© 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. 192910
    Prev
    Next
    INDEX
    Explanations

    qualifications, relations, expected

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

    explaining how or what

    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
     ชาว
    0.54
    ඃ
    0.52
     turt
    0.49
     bú
    0.49
     soch
    0.48
    ëve
    0.48
     காட்டு
    0.48
    дің
    0.47
    欹
    0.46
     букмекер
    0.46
    POSITIVE LOGITS
    Railway
    0.49
    一
    0.47
    Dec
    0.47
    ()
    0.46
    }
    0.46
    パ
    0.46
    cellent
    0.44
    Daddy
    0.44
     advantages
    0.44
    Fault
    0.43
    Activations Density 0.001%

    No Known Activations