© 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. 190057
    Prev
    Next
    INDEX
    Explanations

    writing, believe, production

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

    checking length, bounds, or specific clauses

    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
     з
    0.52
     conversely
    0.51
     т
    0.49
     ACCOUNT
    0.49
    м
    0.47
     сов
    0.46
     INCIDENTAL
    0.46
     rumin
    0.46
     γεν
    0.45
     конфлик
    0.45
    POSITIVE LOGITS
    plied
    0.47
     cellulaire
    0.45
    Օ
    0.44
    vollen
    0.44
    sponge
    0.43
    kelijk
    0.43
    elijke
    0.43
    Into
    0.43
     cytoplas
    0.41
    ترل
    0.41
    Activations Density 0.001%

    No Known Activations