© 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. 161989
    Prev
    Next
    INDEX
    Explanations

    shared risk and protective factors

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

    slightly higher, missing, surplus, adulterated

    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
     Boyfriend
    0.48
    唿
    0.47
     Pizza
    0.46
     कंपटीशन
    0.46
    能
    0.46
    మయ్య
    0.45
     Norman
    0.44
    男友
    0.44
    ل
    0.44
    女友
    0.43
    POSITIVE LOGITS
     fibrillation
    0.48
    ６
    0.47
    ランド
    0.46
    事前に
    0.46
    Jy
    0.45
     chy
    0.44
    YELLOW
    0.44
     atrial
    0.44
     jaunâtre
    0.44
    GeV
    0.43
    Activations Density 0.000%

    No Known Activations