© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104884
    Prev
    Next
    INDEX
    Explanations

    this horrible

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

    Medicare, Buddhism, prospecting

    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
    at
    0.58
    ed
    0.56
    om
    0.55
    d
    0.54
    Movie
    0.51
    Disco
    0.51
    et
    0.50
    aul
    0.50
    ol
    0.49
    os
    0.48
    POSITIVE LOGITS
     century
    0.55
     defenseman
    0.52
     stolet
    0.48
     Khánh
    0.48
     synchrotron
    0.48
     postmodern
    0.48
     Х
    0.48
     ninth
    0.48
     Nghị
    0.47
     brane
    0.47
    Activations Density 0.000%

    No Known Activations