© 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. 204253
    Prev
    Next
    INDEX
    Explanations

    McC or TO followed by a word

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

    quotes and sayings

    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
     diatom
    0.42
    seab
    0.41
    inase
    0.40
    绛
    0.40
    🦜
    0.40
    无法
    0.39
     सामान्य
    0.39
     рр
    0.39
     impossibile
    0.38
     유튜브
    0.38
    POSITIVE LOGITS
    मंड
    0.41
     entreprene
    0.40
     competitiveness
    0.40
     svih
    0.40
    嫵
    0.38
     অতীত
    0.37
     theres
    0.36
     टेलीविजन
    0.36
     sicherlich
    0.36
    ित्य
    0.36
    Activations Density 0.009%

    No Known Activations