© 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. 62439
    Prev
    Next
    INDEX
    Explanations

    to wire

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

    section, fleshy, soul, meaty, Yugoslav

    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
     「
    0.56
    在
    0.50
    적이
    0.48
    [-]
    0.46
    ኃ
    0.46
    ாதார
    0.45
     $"
    0.45
     la
    0.45
     stormwater
    0.45
    站在
    0.44
    POSITIVE LOGITS
     Twentieth
    0.54
    slip
    0.47
    Slip
    0.46
    ulint
    0.46
    віч
    0.43
    Pull
    0.43
     Ελλά
    0.43
    Cin
    0.42
    সৌ
    0.42
    还得
    0.42
    Activations Density 0.000%

    No Known Activations