© 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. 45199
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     to
    -2.97
     for
    -2.67
     have
    -2.52
    \_
    -2.41
     in
    -2.33
     make
    -2.28
     cette
    -2.23
     hacen
    -2.22
    是她
    -2.16
     quieren
    -2.09
    POSITIVE LOGITS
    ↵
    4.03
    剮
    2.72
    ⢧
    2.63
    渼
    2.56
     ウィメンズ
    2.52
    摃
    2.50
    椟
    2.50
     також
    2.50
    能在
    2.42
    떳
    2.42
    Activations Density 0.192%

    No Known Activations