© 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. 53143
    Prev
    Next
    INDEX
    Explanations

    emojis representing concrete objects

    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
    ⥤
    0.45
    不
    0.44
    {};
    0.43
    😪
    0.42
    ীব্র
    0.40
    فكير
    0.40
     infliction
    0.40
    此
    0.40
    😳
    0.39
    ೭
    0.39
    POSITIVE LOGITS
    Â
    0.44
     яхшы
    0.37
     للت
    0.36
     kommenden
    0.36
    بیل
    0.36
    wechsl
    0.36
     ዘዴ
    0.36
    誅
    0.35
    કો
    0.35
     gói
    0.35
    Activations Density 0.006%

    No Known Activations