© 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. 61163
    Prev
    Next
    INDEX
    Explanations

    information, signage, orchestras, home

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

    cyclical, spherical coordinate, expensive

    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
     Castle
    0.53
     Mount
    0.50
     rapeseed
    0.49
     offsetX
    0.49
     trailhead
    0.49
     dimethyl
    0.49
     '~
    0.49
     orchid
    0.49
     wife
    0.48
     ornamental
    0.48
    POSITIVE LOGITS
    мести
    0.54
     находи
    0.47
    пор
    0.47
    ин
    0.47
    form
    0.47
    បង្ហាញ
    0.47
    dari
    0.46
    극
    0.46
    mama
    0.43
    ме
    0.43
    Activations Density 0.000%

    No Known Activations