© 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. 9261
    Prev
    Next
    INDEX
    Explanations

    trained on massive dataset

    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
     vitam
    0.68
     stereotyp
    0.63
     appreci
    0.62
     movieList
    0.61
     Çocuk
    0.61
     stereotypes
    0.59
     CHILDREN
    0.59
     stereotype
    0.59
     متحد
    0.59
    ඖ
    0.58
    POSITIVE LOGITS
    ד
    0.66
    Typically
    0.64
    িস
    0.63
    Humans
    0.63
    <0xE2>
    0.58
     —
    0.57
    Д
    0.57
    Người
    0.57
     온라인
    0.56
     людини
    0.56
    Activations Density 0.425%

    No Known Activations