© 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. 164369
    Prev
    Next
    INDEX
    Explanations

    foreign or abstract words

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

    different nuances

    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
    on
    0.54
    у
    0.50
    |
    0.47
    i
    0.46
    ίας
    0.46
    %
    0.46
    Q
    0.45
     ubiqu
    0.44
     vbox
    0.44
    _
    0.44
    POSITIVE LOGITS
    批评
    0.55
    演员
    0.55
    审美
    0.54
     пев
    0.51
    减轻
    0.51
    狎
    0.51
    하라
    0.50
    钎
    0.50
    干部
    0.50
     ആശയ
    0.50
    Activations Density 0.000%

    No Known Activations