© 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. 83057
    Prev
    Next
    INDEX
    Explanations

    deer and cervids

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

    references to animals in the deer/elk family and their characteristics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects mentions of deer (and closely related cervid species) or references to diseases affecting them.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Chicken
    -0.99
    egg
    -0.93
     Chickens
    -0.93
     Poultry
    -0.91
     chicken
    -0.89
     BIRD
    -0.89
    Birds
    -0.88
     chickens
    -0.88
     parrot
    -0.86
    Penguin
    -0.85
    POSITIVE LOGITS
     deer
    3.31
     Deer
    2.70
    Deer
    2.58
    deer
    2.56
    🦌
    2.27
    鹿
    2.16
     Bambi
    1.92
     antlers
    1.83
     venison
    1.82
     鹿
    1.80
    Activations Density 0.044%

    No Known Activations