© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56474
    Prev
    Next
    INDEX
    Explanations

    time

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

    German words

    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
    Negative Logits
     watches
    0.39
     gec
    0.39
     edges
    0.39
    edges
    0.38
     heaters
    0.38
     council
    0.38
     bed
    0.37
     hatches
    0.37
    軋
    0.37
     dragons
    0.37
    POSITIVE LOGITS
    ldquo
    0.40
    acchati
    0.39
    ühlt
    0.39
    Nom
    0.38
    Juni
    0.38
    च्चय
    0.37
    œur
    0.37
     تهیه
    0.37
    HWND
    0.37
     Bhosle
    0.37
    Activations Density 0.057%

    No Known Activations