© 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. 49223
    Prev
    Next
    INDEX
    Explanations

    years old

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

    most common estimate explanation

    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
    retching
    0.47
    galkan
    0.46
    몰
    0.45
    uyama
    0.44
    ੨
    0.44
    みんな
    0.43
     अमल
    0.43
    egang
    0.41
     떨어
    0.41
    öst
    0.40
    POSITIVE LOGITS
     চালান
    0.46
     hiper
    0.42
     Dolby
    0.42
    গুলি
    0.42
    jose
    0.42
    й
    0.41
    يات
    0.40
     hızlı
    0.40
     Woot
    0.40
    lern
    0.39
    Activations Density 0.000%

    No Known Activations