© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8092
    Prev
    Next
    INDEX
    Explanations

    common punctuation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ৮
    0.28
     in
    0.28
     and
    0.28
    ুনিক
    0.28
    盻
    0.28
     enfermo
    0.27
     Букмекеры
    0.27
    鵃
    0.27
    顐
    0.27
    มีการ
    0.27
    POSITIVE LOGITS
    ar
    0.52
    i
    0.50
     a
    0.50
    a
    0.49
    an
    0.48
    the
    0.47
    c
    0.46
    1
    0.46
    u
    0.45
    er
    0.45
    Activations Density 0.106%

    No Known Activations