© 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. 120531
    Prev
    Next
    INDEX
    Explanations

    aged Gruyère

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

    dialogue starting after quotes

    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
     Dessous
    0.52
    셍
    0.48
    ススメ
    0.46
    naive
    0.46
     Paglin
    0.46
    unie
    0.45
    䒠
    0.45
     hinzufügen
    0.44
    据悉
    0.44
    йт
    0.44
    POSITIVE LOGITS
     kır
    0.50
     s
    0.47
     kendi
    0.47
    INDU
    0.46
     iyi
    0.45
     a
    0.45
     são
    0.44
     yoğun
    0.44
     mip
    0.44
     şu
    0.44
    Activations Density 0.000%

    No Known Activations