© 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. 58681
    Prev
    Next
    INDEX
    Explanations

    resilience

    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
    玧
    -2.97
    狃
    -2.95
    杙
    -2.59
    翃
    -2.58
    ⎆
    -2.58
    
    -2.56
     kemer
    -2.44
     Aktivität
    -2.42
     vorigen
    -2.42
    されてる
    -2.41
    POSITIVE LOGITS
    {
    4.00
    that
    3.02
    屃
    2.61
    (
    2.48
     was
    2.45
     mogą
    2.44
    ON
    2.30
    前に
    2.23
    A
    2.22
    where
    2.19
    Activations Density 0.002%

    No Known Activations