© 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. 30367
    Prev
    Next
    INDEX
    Explanations

    with or without modification

    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
     below
    -0.85
     Below
    -0.73
     yık
    -0.71
    utils
    -0.71
     utils
    -0.69
    Below
    -0.69
     zespo
    -0.69
    ריים
    -0.69
    Sommer
    -0.69
    below
    -0.69
    POSITIVE LOGITS
    Michel
    0.70
     supr
    0.69
    如何
    0.67
    问题
    0.67
    ių
    0.66
    ULTURA
    0.66
     Chry
    0.65
    問題
    0.65
     держа
    0.65
    bari
    0.64
    Activations Density 0.113%

    No Known Activations