© 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. 11869
    Prev
    Next
    INDEX
    Explanations

    the instructions, objects, character, mayor

    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
     mathbf
    0.89
    ophylline
    0.81
    ⎆
    0.81
    浥
    0.81
    돠
    0.80
     ผู้
    0.80
    әне
    0.79
    ນ
    0.79
    rać
    0.79
     ángulo
    0.78
    POSITIVE LOGITS
    2
    0.84
    9
    0.84
    та
    0.83
    8
    0.83
    7
    0.83
    5
    0.81
    1
    0.80
    4
    0.79
    ed
    0.78
    AR
    0.78
    Activations Density 0.000%

    No Known Activations