© 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. 146399
    Prev
    Next
    INDEX
    Explanations

    child equipment

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

    autonomous driving levels and specs

    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
    коно
    0.49
     கிமு
    0.48
    ProfileAction
    0.48
     documento
    0.47
    LogRow
    0.46
     掛け
    0.46
     má
    0.45
    瞥
    0.45
     Букмекер
    0.45
     gyven
    0.45
    POSITIVE LOGITS
    just
    0.51
    shire
    0.50
    ushu
    0.49
    当我们
    0.48
    자
    0.46
     금액
    0.46
    자가
    0.46
    தால்
    0.46
     ill
    0.45
    상이
    0.45
    Activations Density 0.001%

    No Known Activations