© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201799
    Prev
    Next
    INDEX
    Explanations

    administrative limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.61
    int
    0.56
    s
    0.54
    ind
    0.51
    A
    0.51
    em
    0.50
    get
    0.50
    E
    0.50
    <
    0.50
    ?
    0.49
    POSITIVE LOGITS
     toán
    0.57
     Einwill
    0.55
     nirvach
    0.51
     étro
    0.49
    товой
    0.48
    允許
    0.48
     qí
    0.48
    OPENJDK
    0.46
     troviamo
    0.46
    étrique
    0.46
    Activations Density 0.000%

    No Known Activations