© 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. 86866
    Prev
    Next
    INDEX
    Explanations

    string literals and comparisons

    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
     those
    -1.93
     with
    -1.91
     only
    -1.80
     as
    -1.78
     in
    -1.78
     because
    -1.77
     just
    -1.76
     what
    -1.73
     although
    -1.70
     despite
    -1.70
    POSITIVE LOGITS
    えっ
    1.63
    varies
    1.52
     Dinas
    1.52
     participer
    1.45
     commencer
    1.42
     specif
    1.42
     faciliter
    1.39
     terminer
    1.38
     indiquer
    1.37
     retourner
    1.36
    Activations Density 0.052%

    No Known Activations