© 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. 222729
    Prev
    Next
    INDEX
    Explanations

    Diabetes

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

    negative symptoms

    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
    プ
    0.49
    Range
    0.48
    כות
    0.45
     striis
    0.44
     ファイル
    0.44
    في
    0.44
     informazioni
    0.44
    in
    0.44
     appointments
    0.44
    Flo
    0.43
    POSITIVE LOGITS
    糖尿
    0.50
     Bakery
    0.45
    iverr
    0.44
    くと
    0.44
    糖尿病
    0.42
    馍
    0.42
    作业
    0.41
    ifred
    0.41
    雇
    0.41
     Diabetes
    0.40
    Activations Density 0.000%

    No Known Activations