© 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. 6054
    Prev
    Next
    INDEX
    Explanations

    alternative phrasing

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

    entropy, randomness, surprise

    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
    ေါ
    0.53
    aram
    0.47
    uma
    0.47
    guard
    0.46
    畢業
    0.46
    tkinter
    0.44
    sacrifice
    0.44
    ế
    0.44
    obiettivo
    0.42
    mensagem
    0.42
    POSITIVE LOGITS
    надцати
    0.46
     HART
    0.45
    yra
    0.45
    THON
    0.44
     частности
    0.44
     деко
    0.44
     ül
    0.43
    CharCode
    0.43
    샘
    0.43
     uzak
    0.42
    Activations Density 0.000%

    No Known Activations