© 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. 30883
    Prev
    Next
    INDEX
    Explanations

    names with initials

    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
     what
    -2.81
     which
    -2.03
     by
    -1.87
     because
    -1.73
     after
    -1.70
     from
    -1.66
     before
    -1.66
     on
    -1.65
    !!!!
    -1.64
     with
    -1.57
    POSITIVE LOGITS
     chercher
    1.66
     indiquer
    1.65
     représenter
    1.63
     ſol
    1.63
    uhh
    1.61
     MICHAEL
    1.53
     unn
    1.52
     immen
    1.52
     montrer
    1.50
    hmmmm
    1.50
    Activations Density 0.009%

    No Known Activations