© 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. 242554
    Prev
    Next
    INDEX
    Explanations

    dual, charity, Only, It, historical, than

    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
     disposit
    0.50
     passive
    0.46
     PROFESSION
    0.45
    ‌ی
    0.45
    中最
    0.45
    entet
    0.44
    }$)
    0.43
     CONSUM
    0.43
    จากการ
    0.43
     않습니다
    0.43
    POSITIVE LOGITS
     اصلی
    0.51
     मुर
    0.45
     podrás
    0.45
     köş
    0.45
     Pandya
    0.44
    uées
    0.43
    يں
    0.43
     wary
    0.43
     dicen
    0.43
    锕
    0.43
    Activations Density 0.000%

    No Known Activations