© 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. 16272
    Prev
    Next
    INDEX
    Explanations

    select options from lists

    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
    ciela
    -0.92
     If
    -0.87
     during
    -0.86
     or
    -0.85
     अं
    -0.84
    疮
    -0.84
     using
    -0.83
     before
    -0.83
     Universidades
    -0.82
     Sometimes
    -0.82
    POSITIVE LOGITS
     available
    1.41
     настоящий
    1.10
    available
    1.09
     тях
    1.08
     option
    1.08
    considering
    1.04
    Superview
    1.03
    creates
    1.03
     installé
    1.02
    erobic
    1.01
    Activations Density 0.014%

    No Known Activations