© 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. 69757
    Prev
    Next
    INDEX
    Explanations

    below

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

    foreign languages

    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
     रुच
    0.50
    英寸
    0.49
     совета
    0.46
    ANDS
    0.46
    河北
    0.45
    理论
    0.45
     ROBERT
    0.45
    →
    0.45
    研究
    0.44
    นาย
    0.44
    POSITIVE LOGITS
     الص
    0.48
    áni
    0.45
     اقد
    0.43
     añadido
    0.43
     conglomer
    0.43
    ambahkan
    0.43
    ثير
    0.41
     identificación
    0.40
     célébr
    0.40
    ampilkan
    0.39
    Activations Density 0.000%

    No Known Activations