© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 257994
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     jahr
    0.48
    Y
    0.45
     jedan
    0.44
     一个
    0.43
     adunay
    0.43
    參
    0.43
     സ
    0.42
    zá
    0.42
     deeply
    0.42
     بس
    0.42
    POSITIVE LOGITS
     setToDefault
    0.47
    িলো
    0.45
     freshness
    0.43
     клиента
    0.42
    тино
    0.42
     infants
    0.42
    calories
    0.42
    লিখ
    0.41
    𝐼
    0.41
     burdens
    0.41
    Activations Density 0.000%

    No Known Activations