© 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. 32672
    Prev
    Next
    INDEX
    Explanations

    numbers and articles

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

    knowledge dares

    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
     Arden
    0.49
     Sore
    0.48
     Nazareth
    0.48
     Turnbull
    0.46
    ле
    0.45
    слу
    0.45
    쟁
    0.45
     Rowland
    0.44
     periodontal
    0.44
    жор
    0.44
    POSITIVE LOGITS
     እንኳ
    0.46
     skapa
    0.46
     进入
    0.43
     ఇంత
    0.42
    ാനും
    0.42
     ри
    0.41
    舰队
    0.39
     topologies
    0.39
    秞
    0.39
     اعز
    0.39
    Activations Density 0.000%

    No Known Activations