© 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. 120747
    Prev
    Next
    INDEX
    Explanations

    jewel of, but little, future of

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

    Google DeepMind

    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
    វែង
    0.50
    ગાહી
    0.49
    u
    0.47
    in
    0.46
     vets
    0.46
     Frente
    0.45
     तकनीकी
    0.44
     atak
    0.44
    收购
    0.43
     uniforme
    0.43
    POSITIVE LOGITS
    ær
    0.45
     مخصوص
    0.43
    蓯
    0.42
    飯
    0.41
     চে
    0.41
    庐
    0.41
     Hy
    0.40
     جیل
    0.39
    ärt
    0.39
     цін
    0.39
    Activations Density 0.002%

    No Known Activations