© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54340
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

    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
     but
    -1.67
     with
    -1.42
     because
    -1.30
    gunakan
    -1.30
     on
    -1.30
     (
    -1.27
    batik
    -1.23
     and
    -1.22
     through
    -1.20
     in
    -1.19
    POSITIVE LOGITS
     diversos
    1.41
     flera
    1.31
     ڤ
    1.30
     semelh
    1.28
     obwohl
    1.27
     construite
    1.23
     natürlich
    1.20
    wiegend
    1.18
    美国的
    1.17
    ia
    1.16
    Activations Density 0.022%

    No Known Activations