© 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. 121868
    Prev
    Next
    INDEX
    Explanations

    state taxing authorities

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

    contracts and dates

    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
     Джон
    0.52
     जॉन
    0.49
     Вики
    0.49
    ępow
    0.48
     Нью
    0.47
     সফদর
    0.47
     कंडक्टर
    0.47
    👦
    0.47
    lüğ
    0.46
    skich
    0.46
    POSITIVE LOGITS
     dimensionality
    0.50
    s
    0.48
    reduction
    0.44
     Reduction
    0.44
     genes
    0.43
     diminishes
    0.42
     cards
    0.42
     reduction
    0.42
     clicks
    0.41
     enzymes
    0.41
    Activations Density 0.000%

    No Known Activations