© 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. 98502
    Prev
    Next
    INDEX
    Explanations

    outpatient setting

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

    policy scope

    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
     Marian
    0.47
    qos
    0.44
    vart
    0.42
    bellion
    0.40
    ropical
    0.39
    stir
    0.39
     떠
    0.38
    verts
    0.38
    timeouts
    0.37
     fateful
    0.37
    POSITIVE LOGITS
    य
    0.52
     nn
    0.46
     Ту
    0.45
     effic
    0.44
    काइ
    0.44
    踺
    0.43
    ৯
    0.43
     యొక్క
    0.43
     说
    0.43
    ам
    0.42
    Activations Density 0.001%

    No Known Activations