© 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. 11206
    Prev
    Next
    INDEX
    Explanations

    code output and identifiers

    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
    unno
    -1.20
     étanche
    -1.17
    definitely
    -1.17
     adesivo
    -1.15
    }}_
    -1.15
    asca
    -1.14
    やはり
    -1.13
     schilder
    -1.10
     fiasco
    -1.10
     MATTERS
    -1.08
    POSITIVE LOGITS
     it
    1.38
     even
    1.38
     by
    1.29
     or
    1.27
     (
    1.25
     at
    1.24
     this
    1.23
     in
    1.16
     on
    1.12
     during
    1.10
    Activations Density 0.005%

    No Known Activations