© 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. 27542
    Prev
    Next
    INDEX
    Explanations

    vanadium, venus, Tanzania

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

    Van Halen, Van Buren, vancomycin

    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
    '
    0.90
    р
    0.51
    "
    0.48
        
    0.48
    (
    0.46
    E
    0.46
    Z
    0.45
    对
    0.45
    ప
    0.45
    Jun
    0.44
    POSITIVE LOGITS
     vanadium
    0.63
    ल्पन
    0.53
     venus
    0.52
     Tanzania
    0.49
    ণিক
    0.49
    一つの
    0.48
     televisi
    0.47
    廃
    0.47
     मेजब
    0.47
     goodwill
    0.47
    Activations Density 0.027%

    No Known Activations