© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7562
    Prev
    Next
    INDEX
    Explanations

    explaining or needing something

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

    replace with

    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_53_width_65k_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
    𝙽
    0.47
    Всім
    0.41
    𝗥
    0.40
    󠁣
    0.39
    ॐ
    0.38
    \#
    0.38
    ॒
    0.37
    𝗪
    0.37
    uições
    0.37
    AUX
    0.36
    POSITIVE LOGITS
     weird
    0.74
     idk
    0.74
     easier
    0.73
     confusing
    0.72
     عشان
    0.71
     cuz
    0.71
    !!!!!!!!
    0.71
     =>
    0.70
    !!!!!!!!!!!!!!!!
    0.70
    !!!!!!!
    0.69
    Activations Density 0.018%

    No Known Activations