© 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. 196552
    Prev
    Next
    INDEX
    Explanations

    destacar visualizar carrinho

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

    sales landing page

    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
    8
    0.63
    9
    0.62
    6
    0.61
    7
    0.54
    4
    0.53
    M
    0.52
    5
    0.51
    U
    0.50
     杨
    0.47
    0
    0.46
    POSITIVE LOGITS
     carrinho
    0.49
     destaque
    0.48
     visualize
    0.47
     társ
    0.47
     destacan
    0.46
     destacar
    0.45
    äksi
    0.45
     destac
    0.44
     lento
    0.44
     gros
    0.44
    Activations Density 0.001%

    No Known Activations