© 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. 184436
    Prev
    Next
    INDEX
    Explanations

    thrifted finds

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

    lists and descriptions

    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
    あった
    0.49
    vious
    0.47
    UIView
    0.46
    ם
    0.45
    단의
    0.43
     ಸರ್ಕಾರದ
    0.42
    LAW
    0.42
    ᄍ
    0.42
     сути
    0.41
    四年
    0.41
    POSITIVE LOGITS
     permettent
    0.52
     przyjem
    0.52
     Napoli
    0.50
     چیز
    0.49
     bacteri
    0.49
     黄
    0.48
     چگونه
    0.48
     jackpot
    0.48
     üzerine
    0.48
     nổi
    0.48
    Activations Density 0.000%

    No Known Activations