© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100877
    Prev
    Next
    INDEX
    Explanations

    download links and pages

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

    hyperlinks and web URLs, particularly in instructional or technical contexts where users are directed to click, download, or access online resources.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -1.52
     ativar
    -1.41
     that
    -1.39
     zawsze
    -1.27
     gän
    -1.25
     yağı
    -1.23
    tesis
    -1.22
    koala
    -1.22
    cupcake
    -1.22
     tonight
    -1.21
    POSITIVE LOGITS
    They
    1.22
    简约
    1.20
    还不错
    1.14
     years
    1.14
    cillo
    1.11
    ariales
    1.08
     взгляд
    1.05
    );?>
    1.05
    FORM
    1.05
    <h6>
    1.05
    Activations Density 0.163%

    No Known Activations