© 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. 41430
    Prev
    Next
    INDEX
    Explanations

    (Chicago

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

    even, other languages

    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
    ཎ
    0.47
     pageWidth
    0.46
    лната
    0.45
    兎
    0.45
    画面
    0.44
    νά
    0.43
    なっている
    0.43
    ähr
    0.43
    駄
    0.42
    heet
    0.42
    POSITIVE LOGITS
     Browns
    0.47
     Other
    0.46
     മറ്റ്
    0.46
     vors
    0.46
     oppure
    0.45
     McKin
    0.44
     otrzym
    0.44
     Elderly
    0.43
     Waiver
    0.43
     Reid
    0.43
    Activations Density 0.000%

    No Known Activations