© 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. 130749
    Prev
    Next
    INDEX
    Explanations

    specific items and phrases

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

    you are

    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
    <unused2148>
    0.44
    gruppe
    0.44
    gol
    0.43
     Estamos
    0.42
    स्पून
    0.41
    商品を
    0.41
     selección
    0.40
    druk
    0.40
     Roosevelt
    0.40
     Grupo
    0.40
    POSITIVE LOGITS
     는
    0.42
    WindowClass
    0.41
    Label
    0.41
    ாத
    0.41
     rectangles
    0.41
    动态
    0.40
    检查
    0.39
    是个
    0.39
     rectMode
    0.39
     Aesthetics
    0.38
    Activations Density 0.001%

    No Known Activations