© 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. 231215
    Prev
    Next
    INDEX
    Explanations

    individual criteria, Italian native, near Rock

    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
     қа
    0.51
    ล
    0.47
     алюми
    0.47
     रस्सी
    0.46
    Cách
    0.46
     э
    0.46
    ভাষায়
    0.45
     सि
    0.45
     почвы
    0.45
     வளர்ச்ச
    0.45
    POSITIVE LOGITS
    ،
    0.49
    erver
    0.49
     Mitte
    0.49
    ing
    0.48
    ，
    0.47
     تك
    0.46
    ihn
    0.45
     Yuki
    0.45
     Otto
    0.45
    ying
    0.44
    Activations Density 0.000%

    No Known Activations