© 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. 242504
    Prev
    Next
    INDEX
    Explanations

    spell or pronounce

    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
    ából
    0.54
     মাধ্যমিক
    0.52
     ដែល
    0.51
     সূর্য
    0.50
     ပ
    0.48
    ο
    0.47
    enação
    0.45
    ofSeconds
    0.44
    ώσει
    0.44
     }{}_{\
    0.44
    POSITIVE LOGITS
    ﻔ
    0.48
     sug
    0.43
     etiqu
    0.43
    0
    0.42
    ריק
    0.42
    ေ့
    0.41
    хта
    0.41
    TV
    0.40
    WT
    0.40
    TT
    0.40
    Activations Density 0.000%

    No Known Activations