© 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. 94823
    Prev
    Next
    INDEX
    Explanations

    oil, change, Pacific

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

    categorization and options

    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
    Jeremy
    0.47
     récomp
    0.47
    )`,
    0.47
    Conteudos
    0.46
     envoyé
    0.46
    вла
    0.45
     สื
    0.45
     پہنچ
    0.45
    );
    0.44
    TryGetValue
    0.44
    POSITIVE LOGITS
    ಶ್ರ
    0.47
     bluish
    0.45
    ceding
    0.42
     negroes
    0.42
     drap
    0.42
    𝙍
    0.42
     erasing
    0.41
    scaling
    0.41
     ختم
    0.40
     Cheval
    0.40
    Activations Density 0.000%

    No Known Activations