© 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. 26852
    Prev
    Next
    INDEX
    Explanations

    academic and scientific research

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

    phrases that refer to academic research or scientific literature.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ător
    -1.11
     omgeving
    -1.09
     <<<
    -1.08
    りましたが
    -1.08
    کیل
    -1.07
     persönlich
    -1.07
     zukünf
    -1.04
    weightedMode
    -1.03
    layout
    -1.02
     pericolo
    -1.02
    POSITIVE LOGITS
     Ży
    1.21
     recent
    1.20
     I
    1.12
     chrétienne
    1.11
     studies
    1.09
    Recent
    1.09
     vegetales
    1.06
     such
    1.06
     碗
    1.06
    recent
    1.03
    Activations Density 0.063%

    No Known Activations