© 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. 22103
    Prev
    Next
    INDEX
    Explanations

    names, titles, and conjunctions

    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
     utilizadas
    -1.36
    ections
    -1.20
     endwhile
    -1.16
    DispatchToProps
    -1.11
    ransition
    -1.10
    само
    -1.09
     celebridades
    -1.09
    薗
    -1.09
     entsprechenden
    -1.09
     ].
    -1.09
    POSITIVE LOGITS
    他们
    1.40
    我们
    1.35
    3
    1.27
    یتی
    1.16
    ."
    1.14
    4
    1.13
    !
    1.10
    原因
    1.09
     Résultat
    1.08
    ↵
    1.07
    Activations Density 0.048%

    No Known Activations