© 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. 228713
    Prev
    Next
    INDEX
    Explanations

    Jessica Parker

    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
     Obispo
    0.50
     Bowls
    0.49
     pełni
    0.49
     Bowl
    0.48
     Senior
    0.47
    IamPermissions
    0.47
     ஹ
    0.47
    ummer
    0.47
     Mors
    0.46
     Mott
    0.46
    POSITIVE LOGITS
    λά
    0.54
    τα
    0.50
    缫
    0.47
    て
    0.46
    ours
    0.46
    зно
    0.46
    儷
    0.46
    ての
    0.46
    τε
    0.45
    לא
    0.45
    Activations Density 0.000%

    No Known Activations