© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3762
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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_31_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
    $>
    0.29
    ដឹក
    0.29
    éditeur
    0.29
     scary
    0.28
    still
    0.28
    ujjati
    0.28
    Người
    0.28
     fikir
    0.28
     millioner
    0.28
    ’),
    0.28
    POSITIVE LOGITS
     M
    0.36
     G
    0.35
     C
    0.35
     S
    0.35
     A
    0.35
     F
    0.34
     (
    0.33
     E
    0.32
     R
    0.31
     H
    0.31
    Activations Density 0.044%

    No Known Activations