© 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. 4133
    Prev
    Next
    INDEX
    Explanations

    topics and subsequent questions

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

    salient, topic-defining keywords in user queries, especially domain-specific nouns indicating the subject of the question.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    emphas
    0.26
     ہے۔
    0.26
    側面
    0.25
    nfasis
    0.25
     całość
    0.24
    substring
    0.24
    '>
    0.24
     പതി
    0.24
    oggler
    0.24
     esimerkiksi
    0.24
    POSITIVE LOGITS
     travelers
    0.27
    -
    0.26
     and
    0.25
    ographers
    0.25
     medals
    0.25
    wood
    0.24
     किंवा
    0.24
    /
    0.24
     dishonesty
    0.23
    ’
    0.23
    Activations Density 0.567%

    No Known Activations