© 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. 179076
    Prev
    Next
    INDEX
    Explanations

    dates after semicolons

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

    messages from incoming

    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
    dependency
    0.52
    耳机
    0.47
    domain
    0.47
    cups
    0.46
    叶
    0.46
    AAA
    0.46
    domains
    0.46
    p
    0.45
    AUC
    0.45
    strategies
    0.45
    POSITIVE LOGITS
    িত
    0.49
     thousand
    0.49
    -*
    0.48
     trzy
    0.48
     ³
    0.48
     tiga
    0.48
     trois
    0.47
     uomini
    0.47
     purchase
    0.47
     three
    0.46
    Activations Density 0.001%

    No Known Activations