© 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. 53552
    Prev
    Next
    INDEX
    Explanations

    clearly enjoyed

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

    concepts, descriptions, and classifications

    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
     hátsó
    0.45
    려는
    0.45
    ிறார்கள்
    0.44
    লেও
    0.44
    lső
    0.43
     Đầu
    0.43
    ,
    0.42
     Rack
    0.42
    SizeMode
    0.41
     hyperlocal
    0.41
    POSITIVE LOGITS
    OECD
    0.50
    purch
    0.47
     он
    0.44
    삶
    0.42
    Daten
    0.41
    Ｘ
    0.41
     оці
    0.41
     оценка
    0.41
    /*'
    0.41
    origins
    0.40
    Activations Density 0.000%

    No Known Activations