© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33737
    Prev
    Next
    INDEX
    Explanations

    Use of /pkg/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ハイ
    -0.73
    バン
    -0.71
    كن
    -0.71
     först
    -0.70
    AppCompat
    -0.70
    เล็ก
    -0.69
     uch
    -0.69
     siinä
    -0.69
    usize
    -0.69
     ulong
    -0.67
    POSITIVE LOGITS
    noticia
    0.74
    郵便局
    0.74
    変な
    0.74
    ęg
    0.72
    ksis
    0.72
     maksi
    0.71
    それと
    0.70
     medarbe
    0.70
     resolution
    0.68
     всю
    0.68
    Activations Density 0.045%

    No Known Activations