© 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. 82928
    Prev
    Next
    INDEX
    Explanations

    what comes with

    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
    ₁)
    -0.91
     EconPapers
    -0.85
    мання
    -0.82
     Biochim
    -0.79
    лимпий
    -0.79
    MatButtonModule
    -0.79
     lumin
    -0.78
    tauscht
    -0.77
    러나
    -0.77
    aremos
    -0.77
    POSITIVE LOGITS
     comes
    3.33
     accompanies
    2.67
     accompany
    2.55
     come
    2.41
    comes
    2.22
     accompanying
    2.14
     accompanied
    2.13
     associated
    2.11
    Comes
    2.06
     Comes
    1.95
    Activations Density 0.030%

    No Known Activations