© 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. 34097
    Prev
    Next
    INDEX
    Explanations

    cell types, lines, nationwide, pages, samples, earth

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

    categories and context

    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
    Ｔ
    0.43
     approu
    0.42
    ｄ
    0.41
    
    0.41
    ookeeper
    0.41
    ีย
    0.40
     неот
    0.40
     зро
    0.39
    Alternatives
    0.39
     Париж
    0.39
    POSITIVE LOGITS
    defeated
    0.48
     putative
    0.46
     Lalu
    0.44
    ぷ
    0.44
    presumably
    0.43
    grim
    0.43
    ？）
    0.42
     personajes
    0.41
    ဟုတ်
    0.41
     Presumably
    0.41
    Activations Density 0.000%

    No Known Activations