© 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. 4173
    Prev
    Next
    INDEX
    Explanations

    meeting date data break dive

    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
    r
    1.55
    h
    1.55
    re
    1.52
    he
    1.46
    se
    1.44
    де
    1.38
    ла
    1.33
    j
    1.27
    ות
    1.27
    -
    1.27
    POSITIVE LOGITS
    s
    1.43
    َ
    1.41
     รา
    1.38
    辔
    1.37
    ਆਂ
    1.34
    ไม่ใช่
    1.30
    檚
    1.27
    Ds
    1.27
     อ่า
    1.23
     ม
    1.20
    Activations Density 0.164%

    No Known Activations