© 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. 166342
    Prev
    Next
    INDEX
    Explanations

    capillary refill time

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

    Therefore, like

    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
    쪘
    0.46
     SERVICE
    0.45
     housekeeping
    0.45
     shelf
    0.44
    SERVICE
    0.44
    WAR
    0.42
    Conversation
    0.41
    爺
    0.41
    Description
    0.40
    чи
    0.40
    POSITIVE LOGITS
    ṃ
    0.58
     கோட்ப
    0.57
    ariyam
    0.54
    ēc
    0.54
    inot
    0.53
    
    0.53
    esan
    0.52
    𓏧
    0.50
    ayı
    0.50
    armonic
    0.50
    Activations Density 0.001%

    No Known Activations