© 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. 38715
    Prev
    Next
    INDEX
    Explanations

    Q: or . : 1

    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
     klokken
    -1.45
     japonais
    -1.45
     spise
    -1.41
     reager
    -1.38
     kampen
    -1.38
    ziom
    -1.37
     verden
    -1.37
     gamle
    -1.36
    ☠️
    -1.36
     conva
    -1.35
    POSITIVE LOGITS
     now
    2.28
     then
    1.77
     still
    1.71
     always
    1.60
     just
    1.57
     also
    1.55
     go
    1.48
     never
    1.45
     how
    1.44
     don
    1.42
    Activations Density 0.002%

    No Known Activations