© 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. 73377
    Prev
    Next
    INDEX
    Explanations

    golden rule, legendary body, active campaigns

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

    offering improved suggestions

    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
    킹
    0.48
    ﺶ
    0.44
    Geocoder
    0.43
     nhận
    0.43
     aviones
    0.42
    Sunrise
    0.42
    его
    0.42
    ﻞ
    0.42
    김포
    0.41
    ชีพ
    0.41
    POSITIVE LOGITS
     implemented
    0.48
     underlined
    0.48
     underscored
    0.48
     Those
    0.45
    _{[
    0.45
     HCl
    0.44
     aligned
    0.44
     Mugh
    0.43
     شمال
    0.43
    alassemia
    0.43
    Activations Density 0.000%

    No Known Activations