© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95943
    Prev
    Next
    INDEX
    Explanations

    multilingual contexts

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

    computational models and neural networks

    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_31_width_262k_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
    ↵↵
    0.46
     healer
    0.43
     Investments
    0.43
     Moderator
    0.43
     Trump
    0.43
     perut
    0.42
     Curt
    0.41
     Saves
    0.41
     Joanne
    0.41
     Save
    0.41
    POSITIVE LOGITS
     डेफिनेशन
    0.49
     সরাসরি
    0.46
    CodeDict
    0.46
     る
    0.45
    neb
    0.45
     개념
    0.45
     ರಾಷ್ಟ
    0.44
     되고
    0.44
    ക്കുറ
    0.44
     الخم
    0.44
    Activations Density 0.000%

    No Known Activations