© 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. 203925
    Prev
    Next
    INDEX
    Explanations

    specific names and entities

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

    Diamond, Platinum, William

    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
    ர்த
    0.54
    𝗠
    0.52
     BOARDSIZE
    0.51
     ಶಿವ
    0.49
     INumber
    0.49
    𝗡
    0.49
     главное
    0.48
     PLUGIN
    0.48
     IERC
    0.48
    𝚂
    0.48
    POSITIVE LOGITS
    :
    0.51
    '
    0.49
     William
    0.45
    Lat
    0.45
     Diamond
    0.42
     diamond
    0.42
    និង
    0.42
     Jacques
    0.42
    άν
    0.41
    Diamond
    0.40
    Activations Density 0.002%

    No Known Activations