© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 29584
    Prev
    Next
    INDEX
    Explanations

    file structures and project initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     вершин
    0.41
    EDULE
    0.40
     semula
    0.39
    ꘏
    0.39
    lexeme
    0.39
    sparsebundle
    0.39
     приступи
    0.39
    }`;
    0.38
    まとめて
    0.38
    finex
    0.38
    POSITIVE LOGITS
     blazer
    0.40
     Tank
    0.39
     Blazer
    0.38
    port
    0.37
     조성
    0.37
     showcased
    0.37
     Panel
    0.36
     Browse
    0.36
    PORT
    0.36
    Rw
    0.36
    Activations Density 0.000%

    No Known Activations