© 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-16K
    7. 6220
    Prev
    Next
    INDEX
    Explanations

    entry

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     alcuna
    0.94
    色が
    0.93
    renal
    0.92
    wikkel
    0.91
     quinquina
    0.90
    "},
    0.89
    regel
    0.86
    ;",
    0.86
    "\
    0.85
    َل
    0.85
    POSITIVE LOGITS
     fence
    1.04
     gate
    1.02
     gates
    1.02
     Security
    1.00
     Defense
    0.97
     doors
    0.96
     intruders
    0.96
     intruder
    0.95
     gated
    0.95
     Fence
    0.93
    Activations Density 0.398%

    No Known Activations