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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98940
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     diferentes
    -1.09
    NG
    -0.99
     dostęp
    -0.89
     about
    -0.88
    J
    -0.88
     triliun
    -0.85
     estómago
    -0.85
    変わる
    -0.85
     distintas
    -0.84
    A
    -0.84
    POSITIVE LOGITS
     chapel
    1.02
     Kulit
    0.93
     करेंगे
    0.92
     Igual
    0.91
     downtown
    0.91
     funeral
    0.91
    Rote
    0.89
    お子
    0.88
    Cuer
    0.88
    ⅖
    0.87
    Activations Density 0.003%

    No Known Activations