© 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. 14995
    Prev
    Next
    INDEX
    Explanations

    years, it, clicks, English, necessity, Canada, title, light, sight

    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_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
    leggio
    -1.08
    cellona
    -1.05
    PMailer
    -1.02
    rentina
    -1.00
     and
    -0.96
     miei
    -0.96
     Establish
    -0.96
    Jakarta
    -0.95
    EMENTS
    -0.93
    fikasi
    -0.93
    POSITIVE LOGITS
     they
    2.00
     it
    1.95
     there
    1.55
    ).
    1.41
     we
    1.19
    .”
    1.16
     he
    1.15
    。
    1.15
    .
    1.11
    慟
    1.11
    Activations Density 0.074%

    No Known Activations