© 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. 34994
    Prev
    Next
    INDEX
    Explanations

    action state or purpose

    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
    咂
    -1.73
     poë
    -1.72
     persil
    -1.68
     inconvénients
    -1.60
     célè
    -1.58
    点了点头
    -1.48
     sebaiknya
    -1.47
    瞟
    -1.45
     défauts
    -1.40
     mahd
    -1.39
    POSITIVE LOGITS
     after
    1.34
     hurt
    1.25
     thier
    1.20
     hacerlo
    1.17
     gøre
    1.11
     them
    1.09
     doing
    1.07
    𝑙
    1.07
     hittar
    1.07
     ebenso
    1.06
    Activations Density 0.059%

    No Known Activations