© 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. 177615
    Prev
    Next
    INDEX
    Explanations

    early or still

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

    Problem/Solution, Refund

    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
    Estos
    0.54
    ט
    0.54
     convexes
    0.54
    鐧
    0.52
    Geschichte
    0.52
    جرة
    0.51
    르
    0.50
    म्म
    0.48
    믄
    0.48
    طه
    0.47
    POSITIVE LOGITS
    '
    0.53
    cad
    0.51
    word
    0.50
    ashe
    0.48
    ay
    0.48
    ood
    0.48
    ed
    0.48
    bed
    0.47
    ate
    0.47
     been
    0.47
    Activations Density 0.000%

    No Known Activations