© 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. 58061
    Prev
    Next
    INDEX
    Explanations

    class names and CSS selectors

    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
     Vorsitzender
    -0.81
    ValueChanged
    -0.80
     BOG
    -0.79
     エク
    -0.76
    haltung
    -0.75
     VOTE
    -0.75
    pidos
    -0.74
    heiten
    -0.74
    żej
    -0.73
     Vorsitzende
    -0.73
    POSITIVE LOGITS
     Notification
    0.83
    mdc
    0.78
     some
    0.78
     getClient
    0.76
    ql
    0.75
     у
    0.75
    dstuk
    0.74
    !
    0.73
     u
    0.73
     custom
    0.73
    Activations Density 0.035%

    No Known Activations