© 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. 210346
    Prev
    Next
    INDEX
    Explanations

    proper nouns, currencies, numbers

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

    differ from terminal window wide range shockwaves

    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
    agamanam
    0.55
    ug
    0.52
     vro
    0.49
    innerApiCalls
    0.49
    vendor
    0.47
    uk
    0.47
    রা
    0.46
     đậm
    0.45
    诣
    0.44
    getStudentNo
    0.43
    POSITIVE LOGITS
     를
    0.50
    2
    0.50
    3
    0.49
    ˈ
    0.48
    4
    0.47
    6
    0.46
    栤
    0.46
     miliardi
    0.46
     billionaires
    0.45
    Ⅲ
    0.45
    Activations Density 0.000%

    No Known Activations