© 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-65K
    7. 3877
    Prev
    Next
    INDEX
    Explanations

    listing items or explanations

    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_65k_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
    ،
    0.48
    ，
    0.48
    ၊
    0.41
     ،
    0.37
    και
    0.37
    或
    0.36
     ,
    0.35
    $,
    0.33
    >,
    0.33
     ，
    0.32
    POSITIVE LOGITS
     it
    0.46
    ppure
    0.34
    एम
    0.33
     использовании
    0.32
     eventuali
    0.31
     tindakan
    0.31
    <unused2015>
    0.31
     utilisateurs
    0.30
     ისინი
    0.30
    邹
    0.30
    Activations Density 0.243%

    No Known Activations