© 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. 66160
    Prev
    Next
    INDEX
    Explanations

    import paths

    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
    hinter
    -1.05
     Entreprises
    -1.05
    🍝
    -0.93
    béco
    -0.92
     huella
    -0.91
     sostu
    -0.91
    pozy
    -0.90
     telles
    -0.89
    ponses
    -0.88
    ازم
    -0.88
    POSITIVE LOGITS
     our
    1.16
     we
    1.11
     was
    1.05
     We
    1.02
     also
    0.95
    we
    0.95
     Glied
    0.94
    Tracce
    0.87
     here
    0.84
    否认
    0.84
    Activations Density 0.013%

    No Known Activations