© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35050
    Prev
    Next
    INDEX
    Explanations

    Logical structure, group, progression, flow

    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
    有限
    1.44
    奥运
    1.41
    特效
    1.38
    给
    1.38
    亻
    1.34
    ва
    1.33
    膣
    1.31
    ፍተኛ
    1.30
    กรม
    1.30
    周围
    1.29
    POSITIVE LOGITS
    ுங்கள்
    2.20
    siniz
    1.72
    ுள்ள
    1.67
    ek
    1.66
    sa
    1.63
    s
    1.62
    ுள்ளது
    1.59
    of
    1.58
    ss
    1.57
    io
    1.56
    Activations Density 0.008%

    No Known Activations