© 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. 73213
    Prev
    Next
    INDEX
    Explanations

    ordinal positions and rankings

    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
    -1.39
     Both
    -1.38
     dommage
    -1.34
    摃
    -1.33
    OLVED
    -1.32
    чам
    -1.31
     Geografía
    -1.30
     effray
    -1.30
     that
    -1.29
    傒
    -1.29
    POSITIVE LOGITS
    res
    1.43
    ang
    1.38
     at
    1.38
     equality
    1.36
    out
    1.34
     in
    1.34
    á
    1.32
    p
    1.31
    un
    1.29
    ing
    1.28
    Activations Density 0.029%

    No Known Activations