© 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. 66314
    Prev
    Next
    INDEX
    Explanations

    consequences, representation, welding, glows, permitted, Toolbox, NV, metallic

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

    frees, critical, grey, alley, home, city, stability, gc

    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
    (
    0.57
    ICS
    0.48
    LINE
    0.47
     (
    0.46
    0.46
     system
    0.46
     district
    0.45
    ILLE
    0.45
     श्र
    0.44
     ।
    0.44
    POSITIVE LOGITS
     Vestone
    0.58
    profiss
    0.55
     bulunur
    0.52
    pozn
    0.52
     notícia
    0.51
    tDBOutput
    0.51
    ешься
    0.50
     colaborar
    0.50
     draped
    0.49
     eclipsed
    0.49
    Activations Density 0.000%

    No Known Activations