© 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. 47563
    Prev
    Next
    INDEX
    Explanations

    dependent pathway

    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
     blaze
    -0.83
    otype
    -0.74
     Forum
    -0.73
    Forum
    -0.71
    gregor
    -0.70
    odar
    -0.70
     Blaze
    -0.69
    phemy
    -0.69
    ImageField
    -0.68
     mouse
    -0.65
    POSITIVE LOGITS
     Einer
    0.77
     supplé
    0.73
    FDP
    0.73
    censored
    0.68
     expandable
    0.66
    保留
    0.66
    idation
    0.66
     Containment
    0.65
     partial
    0.64
    混
    0.64
    Activations Density 0.065%

    No Known Activations