© 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. 49186
    Prev
    Next
    INDEX
    Explanations

    what do

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

    end of

    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
    ン
    0.51
    ла
    0.50
    К
    0.49
    둘
    0.48
    리
    0.47
    т
    0.47
    ж
    0.47
    ట్
    0.46
    н
    0.45
    א
    0.44
    POSITIVE LOGITS
     paradigma
    0.47
     sequester
    0.47
     paradig
    0.43
    वादियों
    0.43
     epithelial
    0.43
     dónde
    0.43
     vrouwen
    0.43
     Boolean
    0.43
     metas
    0.42
     লুকিয়ে
    0.42
    Activations Density 0.000%

    No Known Activations