© 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. 79960
    Prev
    Next
    INDEX
    Explanations

    book and publication details

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

    support you and colors

    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
    आरपी
    0.50
    땔
    0.44
    렵
    0.43
     catalytic
    0.42
    るとき
    0.41
    뗀
    0.41
    сква
    0.40
    सीएल
    0.40
    뻘
    0.40
     $,
    0.39
    POSITIVE LOGITS
    us
    0.57
    '
    0.54
     或者
    0.52
     benim
    0.50
     καὶ
    0.49
     tượng
    0.48
     ולא
    0.48
     الأصفر
    0.48
     bese
    0.48
     afge
    0.48
    Activations Density 0.009%

    No Known Activations