© 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. 39802
    Prev
    Next
    INDEX
    Explanations

    case citations with numbers

    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
     they
    -1.48
     its
    -1.41
     you
    -1.35
    丷
    -1.27
     universitarios
    -1.23
    guisement
    -1.19
    itoriale
    -1.18
    utches
    -1.15
     aq
    -1.14
    probably
    -1.12
    POSITIVE LOGITS
     before
    1.25
     more
    1.20
     papi
    1.19
    чі
    1.18
     econó
    1.18
    ทั่ว
    1.17
    </em>
    1.16
    睡眠
    1.16
     where
    1.15
    lencia
    1.15
    Activations Density 0.299%

    No Known Activations