© 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. 31523
    Prev
    Next
    INDEX
    Explanations

    product control

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

    punctuation and related words

    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
    et
    0.45
    ariy
    0.45
    )}
    0.44
    )^{*}
    0.43
    作战
    0.43
     sdk
    0.43
     JWT
    0.43
    alu
    0.42
    馕
    0.42
     येईल
    0.42
    POSITIVE LOGITS
    漃
    0.48
    絃
    0.48
     Irm
    0.45
    Ĉ
    0.45
     Nā
    0.45
    ंसी
    0.44
    він
    0.44
     Franti
    0.44
    CHARLES
    0.43
     Δη
    0.43
    Activations Density 0.000%

    No Known Activations