© 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. 22-GEMMASCOPE-RES-131K
    7. 129674
    Prev
    Next
    INDEX
    Explanations

    color values and definitions

    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_22/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
    eeqa
    -1.44
     amerik
    -1.40
     millioner
    -1.38
     Meksiko
    -1.38
     sommer
    -1.37
    tą
    -1.37
     vinter
    -1.35
     blom
    -1.34
     répon
    -1.34
     skå
    -1.33
    POSITIVE LOGITS
     inderdaad
    1.21
    さまざま
    1.21
     a
    1.19
     protože
    1.19
     acestei
    1.16
     fapt
    1.15
     on
    1.11
    ;
    1.09
     culoare
    1.08
     creș
    1.05
    Activations Density 0.002%

    No Known Activations