© 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. 84577
    Prev
    Next
    INDEX
    Explanations

    pots on, them until, in India

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

    project directory or portfolio

    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
     areas
    0.51
     robot
    0.51
     system
    0.51
     victim
    0.50
     willing
    0.50
     waterfront
    0.50
     “
    0.48
     leased
    0.47
     superiore
    0.47
     juc
    0.47
    POSITIVE LOGITS
    emás
    0.46
    และ
    0.46
     थोड़ा
    0.46
    าตุ
    0.46
    奪
    0.44
    டக்கலை
    0.44
    䄳
    0.44
    symmetry
    0.44
    esistenza
    0.44
     моём
    0.43
    Activations Density 0.001%

    No Known Activations