© 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. 160394
    Prev
    Next
    INDEX
    Explanations

    lists of things

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

    hyena(s)

    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
     ik
    0.49
     President
    0.46
     tiket
    0.46
     jl
    0.45
     Ik
    0.45
    現
    0.44
     Political
    0.42
     Hamas
    0.42
     دادن
    0.41
     jard
    0.41
    POSITIVE LOGITS
    寻
    0.53
    之类的
    0.49
     등의
    0.46
    ческие
    0.45
     关闭
    0.44
     ইত্যাদি
    0.44
    ovaná
    0.43
    ⱪ
    0.43
    entric
    0.43
    但这
    0.43
    Activations Density 0.002%

    No Known Activations