© 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. 104459
    Prev
    Next
    INDEX
    Explanations

    web and online content categories

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

    CPI, exploring, parsing, stored data

    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
    Me
    0.48
    Mo
    0.47
    More
    0.47
     Ally
    0.47
    ↵
    0.46
     Wharf
    0.46
     Weller
    0.45
     offer
    0.45
    Do
    0.44
    ’
    0.44
    POSITIVE LOGITS
    存档备份
    0.50
     первым
    0.50
     пережи
    0.49
    cycline
    0.48
    タク
    0.48
     второй
    0.47
     移動
    0.47
     периоди
    0.46
     बनता
    0.46
    рида
    0.46
    Activations Density 0.001%

    No Known Activations