© 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. 14340
    Prev
    Next
    INDEX
    Explanations

    questions about origin or timing

    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
     two
    -1.60
     when
    -1.53
     more
    -1.45
    </em>
    -1.43
    Unfortunately
    -1.41
     immediately
    -1.37
     subsequent
    -1.37
     what
    -1.35
     How
    -1.35
    –
    -1.34
    POSITIVE LOGITS
     which
    1.47
     depuis
    1.41
     WHICH
    1.41
     alltid
    1.39
     welke
    1.29
    ewear
    1.29
     appla
    1.28
     autres
    1.28
    ют
    1.27
     sinds
    1.27
    Activations Density 0.021%

    No Known Activations