© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40191
    Prev
    Next
    INDEX
    Explanations

    opposite of, or, perfect

    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
    Negative Logits
    AG
    0.91
    ON
    0.86
    AT
    0.86
    AR
    0.85
    AU
    0.83
    EP
    0.82
    AF
    0.81
    U
    0.80
    AB
    0.80
    ACH
    0.80
    POSITIVE LOGITS
    ку
    1.05
     mínimo
    1.02
    هِ
    0.98
    ка
    0.95
     takeaways
    0.95
    かを
    0.94
    teile
    0.92
     hiko
    0.92
    ب
    0.91
     machen
    0.89
    Activations Density 0.000%

    No Known Activations