© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104606
    Prev
    Next
    INDEX
    Explanations

    what's going on

    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
    巂
    -2.02
    ᯾
    -1.95
    蕺
    -1.91
    糁
    -1.88
    ované
    -1.84
     élar
    -1.79
    を行いました
    -1.79
    इटम
    -1.79
    厹
    -1.78
     graduación
    -1.76
    POSITIVE LOGITS
     in
    2.53
     they
    1.87
     Although
    1.85
     their
    1.82
     it
    1.73
     Since
    1.72
     with
    1.70
     maintains
    1.65
     about
    1.62
     because
    1.56
    Activations Density 0.009%

    No Known Activations