© 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. 93008
    Prev
    Next
    INDEX
    Explanations

    android layout components

    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
     ২০১
    -0.94
     Smart
    -0.92
     obscene
    -0.88
    ହ
    -0.85
    ensee
    -0.84
     ۲۰۱
    -0.83
    ushchev
    -0.81
    zania
    -0.79
     península
    -0.79
     필
    -0.79
    POSITIVE LOGITS
    coronavirus
    0.85
     vnder
    0.85
     SARS
    0.80
    ifndef
    0.79
     vpon
    0.75
    SARS
    0.73
     השני
    0.71
     Srl
    0.69
    بعاد
    0.69
    жное
    0.69
    Activations Density 0.001%

    No Known Activations