© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17036
    Prev
    Next
    INDEX
    Explanations

    X-bar, barra, top quarks, ħ

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

    mean or average calculations

    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_53_width_65k_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
    ❚
    0.43
    leukin
    0.42
    ❘
    0.40
     Tyne
    0.38
    ભગ
    0.38
    ⨯
    0.38
    폈
    0.38
    ശേഷ
    0.37
     BNP
    0.37
     hydros
    0.37
    POSITIVE LOGITS
    overline
    1.30
    ¯
    1.22
    ̅
    1.05
    >¯</
    1.01
    ̄
    0.99
    ‾
    0.95
    ˉ
    0.93
     barra
    0.88
    bar
    0.85
     barre
    0.81
    Activations Density 0.025%

    No Known Activations