© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30337
    Prev
    Next
    INDEX
    Explanations

    scientific publication and reproducibility

    np_acts-logits-general · gemini-2.5-flash-lite

    academic research methodology terminology, particularly related to meta-analysis and statistical techniques.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on occurrences of the prefix “meta” in compound terms (e.g. “meta‐regression,” “meta‐analysis,” “meta‐analyze”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ari
    -0.83
    渊
    -0.79
     avril
    -0.78
    🍿
    -0.78
    coring
    -0.77
     xếp
    -0.77
     discriminatory
    -0.76
    +'/
    -0.75
     tomar
    -0.75
     coal
    -0.75
    POSITIVE LOGITS
     publication
    1.64
    Publication
    1.34
     published
    1.33
     publish
    1.30
     Publication
    1.29
    publication
    1.25
     confir
    1.11
     reproducibility
    1.09
     veröffentlich
    1.02
     publishing
    0.99
    Activations Density 0.059%

    No Known Activations