© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130922
    Prev
    Next
    INDEX
    Explanations

    at least

    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
    趼
    -1.16
     simply
    -1.13
     sowieso
    -1.12
     merely
    -1.10
    なんだけど
    -1.06
     signifikan
    -1.05
     även
    -1.05
     również
    -1.04
     indeed
    -1.04
     just
    -1.04
    POSITIVE LOGITS
     wenigstens
    1.84
     can
    1.54
     immerhin
    1.45
     now
    1.42
     know
    1.32
    不像
    1.26
     to
    1.21
    至少
    1.19
     zumindest
    1.19
     at
    1.17
    Activations Density 0.011%

    No Known Activations