© 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. 234443
    Prev
    Next
    INDEX
    Explanations

    stages and processes

    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
     firewood
    0.50
    ಲಿದೆ
    0.50
     পূর্ববাংলার
    0.47
     빅
    0.47
    षे
    0.47
     세포
    0.46
     carbohydrate
    0.46
     sandalwood
    0.46
    setEmail
    0.45
     અનુભ
    0.45
    POSITIVE LOGITS
     sicht
    0.55
    ž
    0.55
    Faster
    0.50
    早い
    0.50
    j
    0.50
    n
    0.49
    早期
    0.47
    la
    0.47
    x
    0.46
    ان
    0.46
    Activations Density 0.001%

    No Known Activations