© 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. 37250
    Prev
    Next
    INDEX
    Explanations

    family relations, ingredients, and foreign words

    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
    ğ
    0.54
    nvidia
    0.52
    emple
    0.49
    贺
    0.48
     Juillet
    0.47
    november
    0.47
    j
    0.46
    ἐ
    0.46
    érieure
    0.46
    ro
    0.45
    POSITIVE LOGITS
     Saturdays
    0.48
     alimento
    0.48
     biocompat
    0.48
     недвижи
    0.46
     bốn
    0.46
     primes
    0.45
     ಎಲ್ಲಾ
    0.45
     размера
    0.44
     habitats
    0.44
     thermoplastics
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.