© 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. 10303
    Prev
    Next
    INDEX
    Explanations

    emojis representing shrugging or uncertainty

    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
    atz
    0.94
    ometry
    0.93
    arme
    0.91
    yer
    0.89
    eping
    0.89
     террито
    0.89
    ۳
    0.88
    emp
    0.87
    -
    0.87
    egang
    0.86
    POSITIVE LOGITS
     consape
    1.03
    ا۔
    1.03
    Ẫ
    1.02
     complesso
    1.00
    没有
    0.98
     ainfi
    0.97
     沒有
    0.94
     postavlj
    0.93
     Każ
    0.93
     Gdy
    0.91
    Activations Density 0.000%

    No Known Activations