© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 190066
    Prev
    Next
    INDEX
    Explanations

    entities and concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    API, labels, datasets, safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spider
    0.54
     treadmill
    0.53
     Tarantino
    0.52
    RAR
    0.52
    д
    0.49
     befri
    0.48
     sandwich
    0.47
     blanket
    0.47
     fray
    0.47
     snowboard
    0.47
    POSITIVE LOGITS
     दुर्गेश
    0.55
    ertel
    0.53
     پوچھا
    0.53
     بینک
    0.52
    ates
    0.50
    ٢
    0.50
    authorised
    0.49
    elled
    0.48
    aton
    0.48
     Cálculo
    0.48
    Activations Density 0.000%

    No Known Activations