© 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. 108823
    Prev
    Next
    INDEX
    Explanations

    published

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

    OBD-II data analysis

    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
    ΙΑ
    0.54
    Ъ
    0.54
    aines
    0.52
    ЗА
    0.49
    erno
    0.46
    驰
    0.46
    НА
    0.46
    艾
    0.45
    aird
    0.45
    О
    0.45
    POSITIVE LOGITS
     Jej
    0.55
    ð
    0.54
    čet
    0.48
     ð
    0.48
     đất
    0.47
    }}^{
    0.47
     Verlauf
    0.46
     jej
    0.46
     KX
    0.44
    جة
    0.44
    Activations Density 0.000%

    No Known Activations