© 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. 106539
    Prev
    Next
    INDEX
    Explanations

    section or description beginnings

    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
     Prosecutor
    -0.69
    錠
    -0.68
     first
    -0.67
     placed
    -0.66
     situated
    -0.65
    코
    -0.64
    ausea
    -0.63
    ȧ
    -0.63
    estat
    -0.63
     just
    -0.63
    POSITIVE LOGITS
    opsida
    0.85
     começaram
    0.83
    quiler
    0.82
    детская
    0.82
     Feynman
    0.81
    缂
    0.81
    geordneten
    0.81
    gasse
    0.79
    veau
    0.79
    owol
    0.78
    Activations Density 0.045%

    No Known Activations