© 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. 83803
    Prev
    Next
    INDEX
    Explanations

    winners, invasion, branch, riders

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

    formula, confidently, audience, sort, effectively, confidence, hero

    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
    verted
    0.41
    usely
    0.40
     Paintings
    0.40
     Painting
    0.39
     Lebanese
    0.38
    painting
    0.37
     स्वीकार
    0.37
    テ
    0.36
    鬘
    0.36
    sof
    0.36
    POSITIVE LOGITS
     două
    0.43
     νέ
    0.42
     recibirá
    0.42
     oś
    0.42
     δύο
    0.41
     синх
    0.41
     ullamco
    0.41
     nuevos
    0.40
     paddles
    0.38
     genü
    0.38
    Activations Density 0.010%

    No Known Activations