© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129420
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to questions about animals’ knowledge or cognitive abilities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    animal or human similarities

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

    words and references related to animals.

    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
    ּוֹ
    -1.68
    ־ה
    -1.34
    ַּ
    -1.34
    ֶּ
    -1.21
     خریدار
    -1.21
    וּ
    -1.20
     бампер
    -1.20
    וּ
    -1.20
    ִּ
    -1.16
     église
    -1.09
    POSITIVE LOGITS
     their
    2.11
    Their
    1.77
     humans
    1.49
    ׇ
    1.42
     religieux
    1.38
    According
    1.37
    Unlike
    1.37
     włosów
    1.33
    Different
    1.32
     Their
    1.31
    Activations Density 0.048%

    No Known Activations