© 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. 10-GEMMASCOPE-RES-131K
    7. 15223
    Prev
    Next
    INDEX
    Explanations

    POST method and $_POST variable

    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
    嚒
    -3.08
    genodigd
    -3.02
    蹋
    -2.98
    تیجه
    -2.86
    鲎
    -2.83
    CHREIB
    -2.80
    ⵈ
    -2.78
    潆
    -2.78
    vantaged
    -2.72
     greateſt
    -2.72
    POSITIVE LOGITS
    er
    5.13
    an
    4.25
    e
    4.13
    ing
    4.09
    ed
    3.73
    o
    3.59
    ه
    3.09
    u
    3.08
    en
    2.98
    the
    2.91
    Activations Density 0.011%

    No Known Activations