© 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. 33108
    Prev
    Next
    INDEX
    Explanations

    owl and owls

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

    The neuron detects occurrences of the substring “owl” (in any context or casing).

    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
     Nitro
    -0.77
     Leber
    -0.76
     canard
    -0.74
     myr
    -0.73
     Propor
    -0.72
     Deutsches
    -0.72
    Propor
    -0.71
    icap
    -0.71
    ραγ
    -0.71
    obic
    -0.70
    POSITIVE LOGITS
     owl
    2.36
     owls
    2.19
     Owl
    2.03
     Owls
    1.91
    🦉
    1.76
    owl
    1.55
    Owl
    1.55
     OWL
    1.34
    OWL
    1.21
     nocturnal
    1.09
    Activations Density 0.020%

    No Known Activations