© 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. 65809
    Prev
    Next
    INDEX
    Explanations

    technical programming terms

    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
     to
    -0.98
     LayoutInflater
    -0.93
     onPostExecute
    -0.90
     Stakes
    -0.90
     standards
    -0.89
     several
    -0.88
     there
    -0.88
     .=
    -0.87
    scriptId
    -0.86
    يلات
    -0.85
    POSITIVE LOGITS
     Paesi
    0.99
     firft
    0.99
    rebbe
    0.98
    これらの
    0.97
     canaux
    0.94
     voisins
    0.91
     onix
    0.91
     paff
    0.91
    実際の
    0.89
    vaného
    0.89
    Activations Density 0.042%

    No Known Activations