© 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. 34582
    Prev
    Next
    INDEX
    Explanations

    checking type is

    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
    मंदिर
    1.01
    ments
    0.98
    AM
    0.97
    ं
    0.97
     fins
    0.96
    на
    0.92
     recommand
    0.91
     operatives
    0.91
    วันที่
    0.90
    findings
    0.90
    POSITIVE LOGITS
     didn
    1.23
    𝗷
    1.13
    ᐟ
    1.09
    
    1.09
    ০
    1.07
    𝘆
    1.07
    𝗿
    1.06
    ágenes
    1.05
    𝟬
    1.04
    น
    1.03
    Activations Density 0.000%

    No Known Activations