© 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. 199346
    Prev
    Next
    INDEX
    Explanations

    fiscal year, volume tire, password broadcast

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

    rationality, instrumental, commands

    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
    ف
    0.55
    ON
    0.53
    True
    0.48
    es
    0.47
    e
    0.46
    Shir
    0.46
     preserv
    0.45
    T
    0.44
    م
    0.44
     True
    0.44
    POSITIVE LOGITS
     这是
    0.54
     発
    0.49
    varlak
    0.49
    лкой
    0.48
     活动
    0.48
     Букмекерская
    0.47
     ܗܘ
    0.47
     எழுது
    0.47
     develops
    0.46
     ሽፋ
    0.46
    Activations Density 0.001%

    No Known Activations