© 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. 177553
    Prev
    Next
    INDEX
    Explanations

    sports venue and equestrian

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

    circular definition or circularity

    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
     Tecnología
    0.52
     രൂപ
    0.46
     அல்லது
    0.44
     ប្រ
    0.43
     enunci
    0.42
     Teknologi
    0.41
    }}$
    0.40
     Presbyterian
    0.40
    }-\
    0.40
    ភាគ
    0.40
    POSITIVE LOGITS
     waiters
    0.48
     feel
    0.47
    ሁሉም
    0.45
     bling
    0.44
    感じです
    0.44
     feeling
    0.43
     refreshment
    0.43
     reass
    0.43
     vif
    0.43
     marking
    0.42
    Activations Density 0.002%

    No Known Activations