© 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. 178214
    Prev
    Next
    INDEX
    Explanations

    contact us

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

    cause and effect within structures

    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
    про
    0.49
    с
    0.47
    C
    0.47
     zusätzlichen
    0.46
    е
    0.46
    ర్‌
    0.46
    я
    0.45
    áv
    0.44
     Про
    0.44
    indazol
    0.44
    POSITIVE LOGITS
     liturgy
    0.49
     rituals
    0.46
     rites
    0.45
     conveying
    0.44
     marshes
    0.44
     anum
    0.43
     inspires
    0.43
     romp
    0.43
     reciting
    0.43
     slipping
    0.42
    Activations Density 0.000%

    No Known Activations