© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16279
    Prev
    Next
    INDEX
    Explanations

    first names and titles

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

    meme, surgeon, snow, anime, daily

    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
    aminated
    0.48
     μέσω
    0.48
    হাকে
    0.48
     Sistemas
    0.47
    izarse
    0.45
    UISelectors
    0.45
    stencil
    0.45
    氰
    0.45
    蜱
    0.44
    文件
    0.43
    POSITIVE LOGITS
     Federation
    0.48
     voraus
    0.44
     graag
    0.44
     Irish
    0.42
     Conferences
    0.42
     dances
    0.42
    &
    0.42
     grandi
    0.41
     R
    0.41
     averages
    0.41
    Activations Density 0.008%

    No Known Activations