© 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. 22-GEMMASCOPE-RES-131K
    7. 25797
    Prev
    Next
    INDEX
    Explanations

    finding or discovering something

    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
    是一个
    -1.07
     dann
    -0.95
     pulmonar
    -0.93
    вку
    -0.93
    戦い
    -0.91
     marginLeft
    -0.90
    でしたが
    -0.90
     púb
    -0.90
    toHaveBeenCalled
    -0.90
     such
    -0.88
    POSITIVE LOGITS
     discovered
    1.53
    發現
    1.49
     found
    1.49
    发现
    1.48
     выясни
    1.45
    พบ
    1.41
     descobrir
    1.39
     thấy
    1.38
     обнаружи
    1.33
     revealed
    1.25
    Activations Density 0.091%

    No Known Activations