© 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. 10-GEMMASCOPE-RES-131K
    7. 71336
    Prev
    Next
    INDEX
    Explanations

    agreement and discrepancy

    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_10/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
     bytu
    -1.70
    鸲
    -1.70
     actitudes
    -1.63
    byshev
    -1.63
     vous
    -1.61
    鳎
    -1.57
     nowy
    -1.55
     wtedy
    -1.54
     zatem
    -1.53
    ৢ
    -1.53
    POSITIVE LOGITS
     with
    2.20
     the
    1.57
     only
    1.53
     fers
    1.52
     despite
    1.49
     all
    1.49
    up
    1.44
    遢
    1.43
     longstanding
    1.43
     pastic
    1.40
    Activations Density 0.031%

    No Known Activations