© 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. 111449
    Prev
    Next
    INDEX
    Explanations

    Over

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

    CHARACTER PROFILES

    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
    Produtos
    0.51
    κ
    0.51
    вре
    0.50
     Часто
    0.49
    Questa
    0.47
     Redox
    0.47
    4
    0.46
    嬛
    0.46
    ordable
    0.46
     Flore
    0.46
    POSITIVE LOGITS
     عز
    0.54
     الجمع
    0.54
     جمع
    0.47
     الاجتما
    0.47
     administrations
    0.47
     محبت
    0.45
     ಅಭಿ
    0.44
     adm
    0.44
     فائل
    0.43
     رأ
    0.43
    Activations Density 0.000%

    No Known Activations