© 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. 12197
    Prev
    Next
    INDEX
    Explanations

    starts of clauses because

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

    because, why it works

    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
    ുകളെ
    0.43
    جهات
    0.42
     violators
    0.39
     sebelah
    0.39
     bunları
    0.39
    稅
    0.38
     ব
    0.37
    রাসের
    0.37
    Illegal
    0.37
    혐
    0.37
    POSITIVE LOGITS
    因为它
    0.84
    理由は
    0.70
     ஏனெனில்
    0.65
     क्योंकि
    0.64
    它
    0.64
     its
    0.64
     it
    0.63
     spacious
    0.63
     reasons
    0.63
     because
    0.62
    Activations Density 0.178%

    No Known Activations