© 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. 104219
    Prev
    Next
    INDEX
    Explanations

    software code components

    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
     for
    -1.40
     in
    -1.40
     on
    -1.34
     just
    -1.30
     different
    -1.27
     from
    -1.27
     one
    -1.26
     at
    -1.26
     when
    -1.18
     by
    -1.14
    POSITIVE LOGITS
     inconce
    1.23
     douze
    1.23
    klärt
    1.19
     Creta
    1.14
    _________
    1.14
    Geplaatst
    1.13
    __________
    1.13
     réjou
    1.12
     SIE
    1.12
     fub
    1.12
    Activations Density 0.001%

    No Known Activations