© 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. 135487
    Prev
    Next
    INDEX
    Explanations

    leaving, removed, secret, interior

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

    miles per second

    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
    らず
    0.50
    礫
    0.50
     ціка
    0.49
     طراحی
    0.48
    🍢
    0.48
    ----+---->
    0.47
     Δεν
    0.47
     интересный
    0.46
     غذ
    0.46
    ረጋ
    0.45
    POSITIVE LOGITS
     halves
    0.44
     practitioners
    0.44
     incidence
    0.44
    상
    0.44
     practise
    0.43
    techn
    0.43
     counter
    0.43
     over
    0.43
     let
    0.42
    class
    0.42
    Activations Density 0.000%

    No Known Activations