© 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. 60246
    Prev
    Next
    INDEX
    Explanations

    javascript files and applications

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

    generative AI models

    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
     Jadeja
    0.53
     Unterschiede
    0.52
    скими
    0.50
    标志
    0.48
    وأضاف
    0.48
     органами
    0.46
    涎
    0.46
    构成
    0.45
    ంచెం
    0.44
    堝
    0.43
    POSITIVE LOGITS
     loving
    0.46
     Loving
    0.45
    AS
    0.44
     KAT
    0.42
     biv
    0.41
     obituary
    0.41
     tens
    0.41
    loving
    0.40
    au
    0.40
     kilometres
    0.39
    Activations Density 0.000%

    No Known Activations