© 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. 11879
    Prev
    Next
    INDEX
    Explanations

    december, decode, decentralized, decryption

    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
    ている
    1.87
    {~
    1.86
    ąda
    1.84
     daarom
    1.83
    有助于
    1.83
    }$
    1.82
    没办法
    1.77
    }$.
    1.73
    ❤❤
    1.73
    idays
    1.71
    POSITIVE LOGITS
    ال
    2.48
    byshire
    2.14
    ל
    2.13
    ch
    2.06
    هور
    2.02
     Donde
    2.00
    ক্স
    1.96
    hift
    1.95
    offic
    1.85
    yı
    1.84
    Activations Density 0.249%

    No Known Activations