© 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. 182018
    Prev
    Next
    INDEX
    Explanations

    health services and actions

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

    choose or combine

    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
    丢失
    0.46
    今天是
    0.41
     Ελλάδα
    0.41
     Aktual
    0.41
    何时
    0.40
     nCmdShow
    0.40
    错过
    0.40
    б
    0.39
    谁
    0.39
    埃及
    0.39
    POSITIVE LOGITS
    ing
    0.53
     pouce
    0.51
    estad
    0.49
     berries
    0.49
     Cannon
    0.48
    Semitism
    0.47
     Canon
    0.46
    dung
    0.46
    llan
    0.46
    clarinet
    0.45
    Activations Density 0.000%

    No Known Activations