© 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. 62438
    Prev
    Next
    INDEX
    Explanations

    unrepairable, or cause damage

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

    societal. landlords. sharing. bears

    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
    超
    0.52
    ↵
    0.46
    تف
    0.46
     Recycling
    0.43
    What
    0.43
     Ahmad
    0.42
     Trap
    0.42
     Muhammed
    0.42
     looting
    0.42
     sparking
    0.41
    POSITIVE LOGITS
    férence
    0.54
    រួ
    0.48
    Ě
    0.48
     வரி
    0.47
    juč
    0.47
     yǔ
    0.47
    [];
    0.46
    posición
    0.46
    verdad
    0.46
    Vaterpolo
    0.46
    Activations Density 0.000%

    No Known Activations