© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130478
    Prev
    Next
    INDEX
    Explanations

    introducing explanations or questions

    np_acts-logits-general · gemini-2.5-flash-lite

    working backwards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的
    0.50
     CONTROL
    0.47
    קים
    0.47
    內
    0.46
     WITHOUT
    0.46
     not
    0.45
    円以上
    0.45
    の
    0.45
     MANUAL
    0.44
    内
    0.44
    POSITIVE LOGITS
    dimg
    0.50
     instigated
    0.48
    рения
    0.46
     स्टार्टअप
    0.46
     نی
    0.46
    umption
    0.45
     dissati
    0.45
    astom
    0.45
    vykor
    0.45
     vacances
    0.44
    Activations Density 0.001%

    No Known Activations