© 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. 35995
    Prev
    Next
    INDEX
    Explanations

    list items or code tags

    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
     to
    -1.43
     {
    -1.39
     or
    -1.35
     S
    -1.30
    g
    -1.30
     *
    -1.23
     The
    -1.19
     e
    -1.18
     as
    -1.17
     U
    -1.16
    POSITIVE LOGITS
    Dá
    1.46
    Vá
    1.29
    一歩
    1.27
     fuis
    1.27
    Thema
    1.24
    Продам
    1.23
     veu
    1.23
    Kele
    1.23
     brosse
    1.23
     brisa
    1.21
    Activations Density 0.001%

    No Known Activations