© 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. 22371
    Prev
    Next
    INDEX
    Explanations

    medical oral use

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

    cortisol levels and stress

    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
     їх
    0.60
    ੱਕ
    0.55
     их
    0.55
    PG
    0.52
     unsightly
    0.51
    худ
    0.48
    他們的
    0.47
    Б
    0.45
     kanilang
    0.45
     ಅವರಿಗೆ
    0.45
    POSITIVE LOGITS
    စာ
    0.52
    🍴
    0.50
    avacanam
    0.49
     Museum
    0.49
    celona
    0.49
     Dél
    0.48
     நாட்டில்
    0.48
     Theatre
    0.48
    ²',
    0.48
     书
    0.47
    Activations Density 0.000%

    No Known Activations