© 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. 56354
    Prev
    Next
    INDEX
    Explanations

    cause and object

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

    hand lettering and ancestry

    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
    Negative Logits
    esinin
    0.55
    孃
    0.54
    zag
    0.52
     zelen
    0.51
    zap
    0.51
     abraz
    0.50
     मोह
    0.50
     conspired
    0.48
    }-
    0.48
    benz
    0.47
    POSITIVE LOGITS
    Processes
    0.49
     процессы
    0.48
     entitlements
    0.48
    processes
    0.48
     targ
    0.46
    जन्य
    0.45
     بطور
    0.45
     처리
    0.44
     ngư
    0.43
     theo
    0.43
    Activations Density 0.000%

    No Known Activations