© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63681
    Prev
    Next
    INDEX
    Explanations

    Page_Load event handlers

    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
    Bush
    -0.73
    ([[
    -0.69
     Bush
    -0.68
     Դ
    -0.65
    theguardian
    -0.65
     First
    -0.65
     Hel
    -0.65
     Heb
    -0.65
    jab
    -0.65
    зе
    -0.65
    POSITIVE LOGITS
    沿革
    0.71
    sile
    0.67
     recycled
    0.66
    ⑧
    0.65
     discrimin
    0.63
    Aca
    0.63
    OME
    0.61
    斜
    0.60
     cack
    0.60
    arli
    0.60
    Activations Density 0.085%

    No Known Activations