© 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. 60090
    Prev
    Next
    INDEX
    Explanations

    resigning from positions

    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
    quíni
    -1.69
    providedIn
    -1.63
    玙
    -1.61
     trás
    -1.55
    翃
    -1.52
     этом
    -1.48
     surgir
    -1.45
    >("
    -1.45
    GraphicsUnit
    -1.43
    älle
    -1.42
    POSITIVE LOGITS
     to
    1.46
     from
    1.41
    他已经
    1.36
     كبيرة
    1.34
     they
    1.34
     that
    1.30
     recently
    1.27
     sors
    1.25
     there
    1.25
    に行ってきました
    1.24
    Activations Density 0.024%

    No Known Activations