© 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. 59360
    Prev
    Next
    INDEX
    Explanations

    conditions must be met

    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
    ScopeManager
    -1.59
    葙
    -1.59
    still
    -1.48
    Ý
    -1.46
     plafon
    -1.43
    uded
    -1.42
    typically
    -1.41
    徨
    -1.40
    hlar
    -1.39
     Octobre
    -1.37
    POSITIVE LOGITS
     that
    1.96
     some
    1.94
     if
    1.86
     for
    1.66
     another
    1.49
     include
    1.48
     be
    1.43
     with
    1.42
     including
    1.41
     any
    1.38
    Activations Density 0.072%

    No Known Activations