© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103106
    Prev
    Next
    INDEX
    Explanations

    headquarters

    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_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
    </i>
    -2.66
    𐑂
    -2.41
     quando
    -2.38
    2
    -2.23
     Испа
    -2.22
     weiße
    -2.22
    cised
    -2.20
    ꜆
    -2.19
     WHEN
    -2.19
    LayoutConstraint
    -2.14
    POSITIVE LOGITS
    we
    2.67
    .
    2.36
    <em>
    2.34
     him
    2.30
    ↵
    2.30
    ㌧
    2.25
     preis
    2.25
    <bos>
    2.23
    $*$
    2.22
    ”)
    2.20
    Activations Density 0.005%

    No Known Activations