© 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. 22-GEMMASCOPE-RES-131K
    7. 65361
    Prev
    Next
    INDEX
    Explanations

    Biology and scientific terms

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

    metadata fields in technical documents and code files.

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

    The neuron fires on chunks containing numeric identifiers or version‐style codes (e.g. numbers, dates, IDs, or version strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     by
    -1.39
     this
    -1.36
     their
    -1.34
    angkap
    -1.34
     those
    -1.31
     both
    -1.27
     lamang
    -1.25
     occafion
    -1.23
    jauh
    -1.23
     Vorteil
    -1.21
    POSITIVE LOGITS
    give
    1.23
    𝑧
    1.22
    se
    1.18
    Ausstattung
    1.18
    abetes
    1.16
    ses
    1.13
     humanidad
    1.13
    formerly
    1.09
    volmente
    1.09
    following
    1.07
    Activations Density 0.001%

    No Known Activations