© 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. 34-GEMMASCOPE-RES-131K
    7. 66336
    Prev
    Next
    INDEX
    Explanations

    code syntax closing punctuation

    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_34/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
     so
    -1.54
    ;
    -1.52
     and
    -1.47
     like
    -1.32
     as
    -1.31
     more
    -1.30
     or
    -1.30
     with
    -1.27
     especially
    -1.23
     from
    -1.19
    POSITIVE LOGITS
    )
    2.34
    ())
    1.52
    )
    1.48
    ){
    1.45
    ）
    1.38
    ):
    1.25
    becomes
    1.25
    ){
    1.20
    ):
    1.19
    "){
    1.16
    Activations Density 0.017%

    No Known Activations