© 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. 228559
    Prev
    Next
    INDEX
    Explanations

    exclusive vehicles and partners

    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
    pct
    0.47
    xymatrix
    0.45
    établ
    0.42
    Prove
    0.42
    stv
    0.42
    䡇
    0.41
    íš
    0.41
    xcodeproj
    0.41
    amacare
    0.40
     speci
    0.40
    POSITIVE LOGITS
     Филип
    0.53
    тории
    0.52
    る
    0.52
    ათ
    0.46
    ulitan
    0.46
     రామ
    0.46
     только
    0.46
     wicker
    0.44
     پرته
    0.44
     свобод
    0.44
    Activations Density 0.000%

    No Known Activations