© 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. 53330
    Prev
    Next
    INDEX
    Explanations

    Ayurveda balancing constitutions

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

    common descriptions

    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
    鈮
    0.52
     radionuclides
    0.48
     bombers
    0.48
     militias
    0.47
    営業時間
    0.47
     préciser
    0.47
     FUNDS
    0.47
    亙
    0.46
     設定
    0.46
     思
    0.45
    POSITIVE LOGITS
    hone
    0.54
    rae
    0.52
    coding
    0.45
    fine
    0.44
    v
    0.44
    c
    0.43
    tre
    0.43
     Blackwell
    0.43
    casa
    0.43
    a
    0.42
    Activations Density 0.000%

    No Known Activations