© 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. 98500
    Prev
    Next
    INDEX
    Explanations

    squirrels and monkeys

    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
    cattle
    -0.93
    Shallow
    -0.93
    Cattle
    -0.92
    Kow
    -0.88
    sheep
    -0.86
    Snail
    -0.82
    Spect
    -0.79
    SNA
    -0.79
    shallow
    -0.79
     Cattle
    -0.79
    POSITIVE LOGITS
     squirrels
    2.22
     squirrel
    2.19
    🐿
    1.88
     Squirrel
    1.80
    squirrel
    1.42
    Squirrel
    1.39
     nuts
    1.30
     nut
    1.24
    quirrels
    1.22
     acorn
    1.21
    Activations Density 0.020%

    No Known Activations