© 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. 115796
    Prev
    Next
    INDEX
    Explanations

    location followed by preposition

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

    modern programming concepts

    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
    %.
    0.49
     Jut
    0.48
    <.
    0.47
     রিটার
    0.46
     WITHOUT
    0.46
     without
    0.46
    _.
    0.46
     Ghat
    0.45
     最
    0.45
     个
    0.45
    POSITIVE LOGITS
     გამოყენ
    0.45
    ऑस्ट्रेलिया
    0.44
    ானா
    0.43
    اونلو
    0.43
    ossos
    0.42
    ராக
    0.41
    тились
    0.41
     utilizza
    0.40
    ლე
    0.40
    ام
    0.40
    Activations Density 0.001%

    No Known Activations