© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    what does

    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
    ਰ
    1.66
    ت
    1.35
    ાર
    1.27
    ين
    1.23
    𝘺
    1.21
    ي
    1.19
    𝘵
    1.17
    ং
    1.16
    𝘰
    1.15
    ુ
    1.14
    POSITIVE LOGITS
    ită
    0.91
    heartedly
    0.91
    జేపీ
    0.87
     وعلى
    0.86
    㡺
    0.85
     Họ
    0.84
    Người
    0.84
    ाब
    0.84
    ことがある
    0.83
     attentively
    0.83
    Activations Density 0.090%

    No Known Activations