© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117524
    Prev
    Next
    INDEX
    Explanations

    ViewModel in code

    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
    "
    -0.98
    리고
    -0.89
     odası
    -0.88
    ными
    -0.85
    putstr
    -0.85
     citoy
    -0.82
    sihan
    -0.82
    ͌
    -0.81
    ようやく
    -0.81
     agglomer
    -0.81
    POSITIVE LOGITS
    だそうです
    1.12
    гка
    0.91
     presos
    0.91
    hg
    0.90
    OREA
    0.89
     veía
    0.88
     LinkedIn
    0.88
    deed
    0.87
    laundry
    0.87
     rodzaju
    0.87
    Activations Density 0.004%

    No Known Activations