© 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. 86982
    Prev
    Next
    INDEX
    Explanations

    code snippet keywords

    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
    erialized
    -0.88
    Moda
    -0.85
    tors
    -0.85
    daya
    -0.85
     Beaucoup
    -0.84
     فرود
    -0.84
     Karena
    -0.83
    IZONT
    -0.83
    _"
    -0.83
     домаш
    -0.82
    POSITIVE LOGITS
     Really
    1.10
    (*
    1.09
     String
    1.06
     Len
    1.06
     Must
    1.05
     Close
    1.02
     Get
    1.02
     must
    0.97
     Less
    0.94
    Really
    0.93
    Activations Density 0.015%

    No Known Activations