© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 241
    Prev
    Next
    INDEX
    Explanations

    code comments and technical text

    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
     other
    -1.23
     will
    -1.15
     these
    -1.02
    harmonie
    -1.02
     people
    -0.98
     their
    -0.98
     each
    -0.97
     or
    -0.93
    bourhood
    -0.93
     if
    -0.92
    POSITIVE LOGITS
    新た
    1.00
     embrague
    0.97
     Arra
    0.92
    TRADE
    0.91
    XtraReports
    0.91
     Neale
    0.87
     GIVEN
    0.86
     ingreso
    0.85
     Cognition
    0.85
    PETS
    0.84
    Activations Density 0.000%

    No Known Activations