© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35037
    Prev
    Next
    INDEX
    Explanations

    listing species

    np_acts-logits-general · gemini-2.5-flash-lite

    text patterns in taxonomic descriptions where a genus contains a specific number of species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     during
    -1.52
     then
    -1.27
     During
    -1.24
     while
    -1.23
     various
    -1.16
     will
    -1.11
     would
    -1.09
     {
    -1.06
     specific
    -1.06
     necessary
    -1.05
    POSITIVE LOGITS
     manier
    1.38
     constater
    1.35
     portefeuille
    1.31
    萏
    1.27
     vaisseaux
    1.24
     vinaigre
    1.24
     rigide
    1.23
     appels
    1.23
     melk
    1.22
     solidarité
    1.20
    Activations Density 0.079%

    No Known Activations