© 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. 111575
    Prev
    Next
    INDEX
    Explanations

    exotic, exciting, bizarre, wacky

    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
    \
    -1.72
    //
    -1.52
    -
    -1.33
    }){
    -1.23
    了一
    -1.22
    tt
    -1.22
    ma
    -1.17
    ｒ
    -1.16
    >//
    -1.14
    ule
    -1.13
    POSITIVE LOGITS
     things
    1.70
     variadas
    1.48
     different
    1.48
     various
    1.43
     obrazov
    1.41
     exigencias
    1.38
     when
    1.38
     varying
    1.38
     proč
    1.34
     Einfluß
    1.33
    Activations Density 0.106%

    No Known Activations