© 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. 76003
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and times

    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
    )}]{
    -0.85
    unauthorized
    -0.81
     experiencing
    -0.78
    Isabella
    -0.75
     ndi
    -0.74
    філь
    -0.74
    🍚
    -0.74
    ⑥
    -0.74
    Gebruik
    -0.73
    Unauthorized
    -0.73
    POSITIVE LOGITS
     Qualitative
    0.73
    strerror
    0.70
    utable
    0.68
    valid
    0.67
     apartheid
    0.67
    fac
    0.66
     '*')
    0.66
     valid
    0.66
    elemField
    0.65
    lites
    0.65
    Activations Density 0.073%

    No Known Activations