© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98880
    Prev
    Next
    INDEX
    Explanations

    body parts and actions

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

    phrases related to offering or providing assistance, particularly with the word "hand".

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Skocz
    -1.63
    閪
    -1.49
     денег
    -1.46
    静岡
    -1.46
    Ｑ
    -1.44
    WRENCE
    -1.42
    xyl
    -1.40
     instituição
    -1.37
    rierten
    -1.36
    luas
    -1.36
    POSITIVE LOGITS
     doesn
    1.70
    也知道
    1.67
     are
    1.66
     to
    1.66
     was
    1.59
     but
    1.59
    us
    1.58
    om
    1.55
    am
    1.55
     didn
    1.55
    Activations Density 0.012%

    No Known Activations