© 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. 117383
    Prev
    Next
    INDEX
    Explanations

    graphics that, searching for, expense of, body tethering

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

    floating / attached mechanisms

    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
    َّ
    0.54
    اعدة
    0.52
     récent
    0.50
    "،
    0.49
    "।
    0.49
    管理局
    0.49
     Smoke
    0.48
    خصص
    0.47
    ،
    0.47
    ónicos
    0.47
    POSITIVE LOGITS
    tm
    0.54
     extrav
    0.51
     ಜ
    0.49
    tl
    0.49
    rs
    0.48
    tura
    0.48
    ngl
    0.48
    ty
    0.47
    rt
    0.47
    tle
    0.47
    Activations Density 0.000%

    No Known Activations