© 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. 151733
    Prev
    Next
    INDEX
    Explanations

    feedlot alley

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

    `None` or `decide`

    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
    0.64
     de
    0.60
     U
    0.52
     or
    0.50
     Epstein
    0.50
     Winkler
    0.47
    iene
    0.47
    і
    0.46
     North
    0.46
    s
    0.46
    POSITIVE LOGITS
     angustato
    0.52
     ambayo
    0.52
    utada
    0.51
    শুধ
    0.50
     escolher
    0.48
    лизации
    0.48
     သူ့
    0.48
     전에
    0.47
    लिनी
    0.47
     aquilo
    0.47
    Activations Density 0.000%

    No Known Activations