© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30740
    Prev
    Next
    INDEX
    Explanations

    speaking with emoticons

    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_all/layer_41_width_262k_l0_big
    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
     appunto
    0.47
    ருங்கள்
    0.42
    ວນ
    0.42
    美女
    0.40
     footballers
    0.39
     hypocrisy
    0.39
    鷸
    0.39
     непло
    0.39
     músicos
    0.39
     Boynton
    0.39
    POSITIVE LOGITS
    ~!
    0.76
    ~
    0.75
    🥺
    0.75
    ㅠㅠ
    0.67
     ♡
    0.65
    ヾ
    0.63
    呜
    0.63
    ~)
    0.63
    (*´
    0.62
     uh
    0.62
    Activations Density 0.007%

    No Known Activations