© 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. 217374
    Prev
    Next
    INDEX
    Explanations

    alternator wiring

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

    ROC curve analysis

    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
     هستند
    0.50
    kannya
    0.50
    rantes
    0.50
    [_
    0.48
     पुरंदरे
    0.47
     ugl
    0.46
    ٫
    0.45
     কথোপ
    0.45
    bentuk
    0.44
     ইপিআর
    0.44
    POSITIVE LOGITS
     dock
    0.51
     !",
    0.48
    í
    0.47
    ob
    0.46
    processors
    0.44
    Lus
    0.43
    ři
    0.42
     lumber
    0.42
     docks
    0.42
    ooi
    0.42
    Activations Density 0.000%

    No Known Activations