© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111354
    Prev
    Next
    INDEX
    Explanations

    scholarly writings and publications

    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
     ľudí
    -1.90
     naše
    -1.88
    𖧵
    -1.82
     helicópter
    -1.80
     môže
    -1.76
     využí
    -1.72
     opravdu
    -1.72
    ꪔ
    -1.70
     musí
    -1.68
    来自于
    -1.68
    POSITIVE LOGITS
    In
    2.14
    Since
    1.88
    L
    1.84
    ).
    1.68
     :
    1.65
    While
    1.63
    During
    1.63
     conosciuto
    1.63
     abitanti
    1.62
     Empfindung
    1.59
    Activations Density 0.028%

    No Known Activations