© 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. 9494
    Prev
    Next
    INDEX
    Explanations

    `(` or `$` followed by number or `(`

    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
     ইহাতে
    0.70
     Talks
    0.67
    0
    0.66
     bursting
    0.66
     黃
    0.66
     Adding
    0.65
     Upload
    0.65
     Yellow
    0.65
     Ну
    0.65
     Explosion
    0.65
    POSITIVE LOGITS
     domaines
    0.77
    ]，
    0.73
     situado
    0.71
    噎
    0.71
    ต่ำ
    0.69
    க்கான
    0.67
    ugat
    0.66
    সীম
    0.66
    ímica
    0.65
    舶
    0.65
    Activations Density 0.001%

    No Known Activations