© 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. 10-GEMMASCOPE-RES-131K
    7. 128410
    Prev
    Next
    INDEX
    Explanations

    days of the week, medical conditions, or related nouns

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

    proper nouns and organization names.

    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_10/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
     if
    -1.80
    ’
    -1.45
    '
    -1.44
     '
    -1.43
    就能
    -1.42
     –
    -1.41
    -1.38
    最
    -1.38
    就可以
    -1.37
         
    -1.34
    POSITIVE LOGITS
     of
    1.77
     to
    1.74
     것입니다
    1.63
    calça
    1.54
     them
    1.54
     anpassen
    1.52
    ⻓
    1.48
     angepasst
    1.44
     Warum
    1.43
    meteries
    1.41
    Activations Density 0.170%
    No Known Activations