© 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. 195556
    Prev
    Next
    INDEX
    Explanations

    items aside

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

    biological, media, and health topics

    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
    ढ़ाई
    0.46
    த்துக்கும்
    0.44
    거나
    0.43
     डिपॉजिट
    0.42
     sone
    0.42
    ेंशियल
    0.41
    ɒ
    0.41
    น
    0.40
    പ്പ
    0.40
    的市场
    0.40
    POSITIVE LOGITS
     sexuales
    0.47
    ;
    0.47
     зокрема
    0.47
     schematic
    0.45
     laterales
    0.44
     intracellular
    0.43
     extracellular
    0.43
    anatom
    0.43
     anatom
    0.42
     MainActivity
    0.42
    Activations Density 0.001%

    No Known Activations