© 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. 138451
    Prev
    Next
    INDEX
    Explanations

    account, compatible, fill, players, blueberry

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

    explicitly stating what to do

    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
    йы
    0.51
    🗑
    0.47
     поведение
    0.46
    셈
    0.45
     модели
    0.44
    вать
    0.43
    modelo
    0.43
    贱
    0.42
    ப்பை
    0.42
     уйнау
    0.42
    POSITIVE LOGITS
     matrimon
    0.46
     υψη
    0.46
     hipert
    0.46
     needing
    0.45
     interiors
    0.44
     raster
    0.44
     fare
    0.43
     need
    0.43
     dictionaries
    0.43
     পত্রিকা
    0.42
    Activations Density 0.001%

    No Known Activations