© 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. 34-GEMMASCOPE-RES-131K
    7. 86780
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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_34/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
     potrebbero
    -0.71
    GOTO
    -0.71
    rophoresis
    -0.71
     disponibile
    -0.69
    bilder
    -0.68
     Palermo
    -0.68
     غرب
    -0.68
     Yards
    -0.68
    REFERRED
    -0.67
    ベーション
    -0.67
    POSITIVE LOGITS
    Nissan
    0.84
    razit
    0.84
    tekend
    0.84
     Nissan
    0.82
     Phal
    0.79
    Wax
    0.79
     Sha
    0.78
    iteln
    0.76
     carnival
    0.75
     Gis
    0.74
    Activations Density 0.034%

    No Known Activations