© 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. 249964
    Prev
    Next
    INDEX
    Explanations

    power on/off

    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
    取り付け
    0.58
     старо
    0.51
     izvr
    0.49
    ўна
    0.44
     Elektrokhimiya
    0.44
    મેન્ટ
    0.44
     chegada
    0.43
    に進
    0.43
     realizing
    0.43
    🏘
    0.43
    POSITIVE LOGITS
    d
    0.64
     Operation
    0.56
     Ot
    0.54
     Packaging
    0.54
    ys
    0.53
    ul
    0.52
     Requests
    0.52
     Oper
    0.52
     Stair
    0.50
     Form
    0.49
    Activations Density 0.001%

    No Known Activations