© 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. 85546
    Prev
    Next
    INDEX
    Explanations

    phrase describing artistic subjects or descriptive titles

    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
     QUÉ
    -1.65
     TÉ
    -1.62
     célè
    -1.55
     DÉ
    -1.49
     HISTORIA
    -1.47
     TRABAJO
    -1.47
     CONSE
    -1.45
     oiseau
    -1.43
     verzi
    -1.42
     INFORMACIÓN
    -1.41
    POSITIVE LOGITS
     with
    1.70
     by
    1.61
     from
    1.60
     in
    1.58
     it
    1.44
    :
    1.44
    t
    1.42
     With
    1.31
    </em>
    1.30
     some
    1.30
    Activations Density 0.059%

    No Known Activations