© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    division by a quantity

    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
    捌章
    0.42
    叁章
    0.41
    ابط
    0.41
     Зак
    0.40
    ',['
    0.40
     कहानियां
    0.40
     Він
    0.40
    ជា
    0.39
     შორის
    0.39
     groot
    0.38
    POSITIVE LOGITS
    '
    0.44
    rne
    0.41
     the
    0.39
     numbers
    0.39
     divisor
    0.39
     virtue
    0.39
    ezing
    0.39
     your
    0.39
    ethylamine
    0.37
    ző
    0.37
    Activations Density 0.002%

    No Known Activations