© 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. 85986
    Prev
    Next
    INDEX
    Explanations

    key/critical concepts

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

    offset and position adjustments

    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
     заканчи
    0.45
     workshop
    0.44
     upfront
    0.43
     योजना
    0.42
    続
    0.42
    skins
    0.41
     చిహ్
    0.41
    executable
    0.40
     mathsize
    0.40
    schema
    0.39
    POSITIVE LOGITS
    关键
    0.48
     Ζ
    0.47
    Ζ
    0.47
     Ciências
    0.46
    ʋ
    0.45
     tř
    0.44
    URNIZOR
    0.44
     Dubna
    0.44
     dificuldade
    0.43
     aço
    0.43
    Activations Density 0.000%

    No Known Activations