© 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-16K
    7. 11992
    Prev
    Next
    INDEX
    Explanations

    showing actions or results

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

    show and demonstrate

    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_16k_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
    า
    0.87
    س
    0.87
     OPPO
    0.83
    го
    0.73
    z
    0.73
    ल
    0.73
    ર
    0.70
    ר
    0.70
    ي
    0.69
     CSR
    0.68
    POSITIVE LOGITS
    SHOW
    0.72
    Showing
    0.68
     zeigen
    0.67
     montrent
    0.64
    Show
    0.63
    ப்பட்டுள்ளது
    0.61
     шоу
    0.59
     보여
    0.59
     zeigte
    0.56
     نمایش
    0.56
    Activations Density 0.329%

    No Known Activations