© 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. 136064
    Prev
    Next
    INDEX
    Explanations

    electrical wires, their path, surface without

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

    states and arrangements

    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
    ة
    0.66
    方面的
    0.52
     milhões
    0.48
     اړه
    0.48
     wichtiger
    0.48
     gelegen
    0.47
     jährlich
    0.47
    Ꮘ
    0.47
     heute
    0.45
     crédito
    0.45
    POSITIVE LOGITS
    த்தினை
    0.57
    ภาย
    0.51
    pairwise
    0.50
    jobSize
    0.50
    vdd
    0.47
    apl
    0.47
    getBlueTeam
    0.46
    拡張
    0.46
    に入れて
    0.46
     pairwise
    0.46
    Activations Density 0.001%

    No Known Activations