© 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. 53-GEMMASCOPE-2-RES-262K
    7. 9468
    Prev
    Next
    INDEX
    Explanations

    key-value pairs or item definitions

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

    tokens that are part of headings, titles, or emphasized proper nouns (section headings and other capitalized/emphasized names).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
    𒃻
    0.29
    餑
    0.28
    曬
    0.27
     بیٹنگ
    0.27
     койма
    0.26
    ྜ
    0.26
    <unused622>
    0.26
    !!!");
    0.26
     teamTable
    0.26
    माइंडर
    0.25
    POSITIVE LOGITS
    ,
    0.47
    ;
    0.38
    .
    0.38
    /
    0.37
     (
    0.37
     and
    0.35
    (
    0.34
    :
    0.33
    |
    0.33
    -
    0.32
    Activations Density 0.399%

    No Known Activations