© 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. 13101
    Prev
    Next
    INDEX
    Explanations

    lists and tables

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

    markdown table headers

    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
    ätzen
    0.41
    Voici
    0.40
    зацию
    0.40
    since
    0.39
    Below
    0.38
    Guidelines
    0.38
    쪼
    0.37
    larini
    0.37
     revise
    0.37
    Berikut
    0.37
    POSITIVE LOGITS
    rlen
    0.46
    YN
    0.40
    են
    0.40
     drooping
    0.39
    metto
    0.39
     rows
    0.39
     висо
    0.38
    pulsewidth
    0.38
     volante
    0.38
    难
    0.38
    Activations Density 0.010%

    No Known Activations