© 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. 54337
    Prev
    Next
    INDEX
    Explanations

    options, arguments, and parameters

    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
     even
    -1.46
     many
    -1.41
     more
    -1.38
     when
    -1.37
     some
    -1.34
     these
    -1.21
     every
    -1.20
     this
    -1.19
     each
    -1.18
     at
    -1.16
    POSITIVE LOGITS
     choisir
    1.13
    の作成
    1.08
     .
    1.08
     paramètres
    1.07
     choice
    1.07
    &
    1.07
     abd
    1.05
    旁边
    1.05
     abf
    1.04
    そこまで
    1.03
    Activations Density 0.005%

    No Known Activations