© 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. 3859
    Prev
    Next
    INDEX
    Explanations

    people who collect

    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
    ser
    0.81
    a
    0.75
    이면
    0.73
    ीत
    0.72
    йся
    0.71
    son
    0.69
     Grü
    0.68
    ss
    0.68
     undersigned
    0.68
     Architecture
    0.66
    POSITIVE LOGITS
    𝘶
    0.93
    го
    0.91
    バトル
    0.81
    อย่าง
    0.80
    们
    0.80
    という
    0.79
    ുകൾ
    0.79
    ുകളും
    0.79
    ما
    0.79
     musculaire
    0.78
    Activations Density 0.000%

    No Known Activations