© 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. 47559
    Prev
    Next
    INDEX
    Explanations

    up, down, left, right, top

    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
    canestro
    -0.83
    Ranks
    -0.74
    ција
    -0.73
    lerinden
    -0.73
    íferos
    -0.72
     best
    -0.71
     backend
    -0.71
     commitment
    -0.71
    KJV
    -0.69
     varsa
    -0.68
    POSITIVE LOGITS
    most
    1.24
    पु
    0.87
    hydrates
    0.83
    Margin
    0.82
    부터
    0.80
    ffine
    0.80
     Of
    0.80
    MOST
    0.79
    министра
    0.79
    ²+
    0.77
    Activations Density 0.031%

    No Known Activations