© 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. 7401
    Prev
    Next
    INDEX
    Explanations

    GUI programming and C++ streams

    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
     selben
    -3.33
    ’
    -2.73
     But
    -2.42
    旆
    -2.41
     Ganzen
    -2.36
    ’，
    -2.34
    𔘓
    -2.34
     einzigen
    -2.34
     начинают
    -2.33
    〮
    -2.33
    POSITIVE LOGITS
    .
    3.09
    ↵↵
    2.69
    玧
    2.25
    柃
    2.22
    ↵
    2.13
    getPackageName
    1.95
    ଽ
    1.94
    /")
    1.91
    狆
    1.91
     梨
    1.90
    Activations Density 0.001%

    No Known Activations