© 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. 20831
    Prev
    Next
    INDEX
    Explanations

    $\theta$ and radius

    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
    -
    -3.05
    ，
    -2.84
    There
    -2.73
    ?
    -2.64
     -
    -2.58
    e
    -2.58
    Even
    -2.56
    During
    -2.50
    However
    -2.48
    Although
    -2.47
    POSITIVE LOGITS
    ৢ
    4.19
    鲠
    3.44
    髕
    3.34
    塍
    2.98
    
    2.94
    ⩴
    2.89
    쫀
    2.84
    ꪔ
    2.84
    ⩕
    2.81
    塒
    2.78
    Activations Density 0.045%

    No Known Activations