© 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. 250828
    Prev
    Next
    INDEX
    Explanations

    `spoilers have`, `email to`, `shall inherit`

    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
     Wasch
    0.52
    pard
    0.51
    dat
    0.50
    d
    0.49
    parseFloat
    0.48
     Lin
    0.48
    subplot
    0.47
    pun
    0.47
    siz
    0.47
    washed
    0.47
    POSITIVE LOGITS
     utopian
    0.57
     philanthropic
    0.56
     philanth
    0.54
    の世界
    0.51
     sociocultural
    0.50
     zéro
    0.49
    ୃ
    0.49
     demonstration
    0.48
     obligatory
    0.47
    โบ
    0.47
    Activations Density 0.001%

    No Known Activations