© 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. 31-GEMMASCOPE-2-RES-16K
    7. 91
    Prev
    Next
    INDEX
    Explanations

    flow provides

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Ab
    0.36
    ただし
    0.36
    Causes
    0.36
    <0x0D>
    0.36
    แต่
    0.35
    しかし
    0.34
    Result
    0.34
    False
    0.34
    C
    0.34
    Phosph
    0.33
    POSITIVE LOGITS
    வின்
    0.64
     యొక్క
    0.63
    ’
    0.61
    ாவின்
    0.60
    த்தின்
    0.59
    本身的
    0.57
     itself
    0.56
    യുടെ
    0.56
     sendiri
    0.53
    自身的
    0.53
    Activations Density 1.175%

    No Known Activations