© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19934
    Prev
    Next
    INDEX
    Explanations

    class goesactivities takeconnection betweenrelated keywordssharing experiencesno thanksthe song

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    込んで
    0.43
    ﻔ
    0.43
    <0x80>
    0.41
    си
    0.41
    따
    0.40
     коль
    0.39
     מב
    0.39
     mjesto
    0.38
     razie
    0.38
     격
    0.37
    POSITIVE LOGITS
     ಹಲವಾರು
    0.53
    are
    0.51
     undertook
    0.49
     একাধিক
    0.48
    क्यूमेंट
    0.48
     الشركات
    0.47
    tStart
    0.44
    is
    0.44
    hte
    0.43
     നിരവധി
    0.43
    Activations Density 0.001%

    No Known Activations