© 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. 70656
    Prev
    Next
    INDEX
    Explanations

    are you wanting to

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

    cause and effect

    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
    Eco
    0.46
    Produto
    0.43
    In
    0.43
     geweest
    0.43
    Market
    0.41
    Barrel
    0.41
    Jake
    0.40
    Π
    0.40
    なのか
    0.40
    Пре
    0.39
    POSITIVE LOGITS
     刺繍
    0.55
     CHANGES
    0.52
    qh
    0.51
    ִי
    0.49
    robespierre
    0.47
     ทํา
    0.47
    followlike
    0.47
     世界
    0.47
     EPI
    0.47
    躹
    0.47
    Activations Density 0.003%

    No Known Activations