© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements

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

    percentage ranges and counts

    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
    alth
    0.26
    ലോ
    0.26
    εια
    0.25
    ಲ್ಲೂ
    0.25
     ၁
    0.25
    흔
    0.24
    ️⃣
    0.24
     ২
    0.24
    ੰ
    0.24
     ১
    0.23
    POSITIVE LOGITS
    hundred
    0.37
    dozen
    0.34
     $\%$
    0.34
     dozen
    0.33
     '%'
    0.32
    %$
    0.31
     \%$
    0.31
     hundreds
    0.30
    thousand
    0.30
    Average
    0.30
    Activations Density 0.370%

    No Known Activations