© 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. 193502
    Prev
    Next
    INDEX
    Explanations

    health issues

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

    specific topics like demographics, patient reports, creativity

    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
     dBASE
    0.51
    აქ
    0.49
     পাকসেন
    0.49
    怪
    0.48
    閇
    0.47
    کرد
    0.47
    푯
    0.47
    نا
    0.46
    ﺫ
    0.46
     varía
    0.46
    POSITIVE LOGITS
    one
    0.56
     แจ
    0.48
    on
    0.45
     eight
    0.45
    วาม
    0.45
    ov
    0.45
    ophone
    0.45
    ומי
    0.45
     an
    0.44
    во
    0.44
    Activations Density 0.000%

    No Known Activations