© 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. 121360
    Prev
    Next
    INDEX
    Explanations

    end of phrase punctuation

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

    energy surge, efficiency, translation, nucleus

    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
     знания
    0.46
     ఎవ
    0.44
     numerals
    0.44
     паз
    0.43
     diffé
    0.43
     distribusi
    0.43
     pemrograman
    0.43
    ଢ
    0.42
     읽
    0.42
     berbeda
    0.41
    POSITIVE LOGITS
     Clooney
    0.49
    rollers
    0.47
    óch
    0.45
    ORY
    0.45
     Mulder
    0.45
     দৃষ্টি
    0.44
    nout
    0.44
    startswith
    0.44
     Ashby
    0.44
    ني
    0.44
    Activations Density 0.001%

    No Known Activations