© 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. 99568
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by opening brace

    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
    issez
    -1.22
    itzende
    -1.00
    ≃
    -0.99
    бір
    -0.98
    bø
    -0.92
     dévou
    -0.92
     מי
    -0.91
    埃及
    -0.91
     ujednoznacz
    -0.91
    isez
    -0.90
    POSITIVE LOGITS
    ものに
    0.99
     and
    0.98
     {
    0.92
     mismas
    0.91
     that
    0.90
     weihnachten
    0.87
     throws
    0.85
     attiva
    0.84
    那人
    0.84
     saw
    0.84
    Activations Density 0.011%

    No Known Activations