© 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. 221446
    Prev
    Next
    INDEX
    Explanations

    USA Prize nomination

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

    truth claims, comfort aspect

    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
    น้ำ
    0.47
     પાણી
    0.47
     үз
    0.47
    仹
    0.46
    SELL
    0.45
    ть
    0.45
    䨪
    0.45
    toEqual
    0.44
    نامه
    0.44
    بيع
    0.44
    POSITIVE LOGITS
     amu
    0.50
     cocker
    0.46
     administrator
    0.46
     adopter
    0.46
     choć
    0.45
     hỗ
    0.45
     auraient
    0.45
     sequencer
    0.44
     clearances
    0.44
    |-|-
    0.44
    Activations Density 0.000%

    No Known Activations