© 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. 77005
    Prev
    Next
    INDEX
    Explanations

    so it

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

    harmful power dynamics in scenarios

    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
    ]=[
    0.42
    ዐ
    0.40
    膀
    0.40
    茧
    0.39
     প্রার্থী
    0.39
    θ
    0.39
     ро
    0.38
     endors
    0.38
    binder
    0.38
     Thames
    0.38
    POSITIVE LOGITS
    শ্যক
    0.50
    ելի
    0.49
    usega
    0.48
    بانی
    0.47
    itié
    0.46
    悧
    0.46
     descansar
    0.45
    ServiceProvider
    0.44
    ህን
    0.44
    ルフ
    0.43
    Activations Density 0.002%

    No Known Activations