© 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. 10-GEMMASCOPE-RES-131K
    7. 59550
    Prev
    Next
    INDEX
    Explanations

    mammal / mammals

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

    This neuron activates for the word "mammals" and related terms like "mammalian".

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

    The neuron activates on words referring to mammals or the mammalian lineage (e.g. “mammals,” “mammalian,” “eutherian,” “marsupial”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鼕
    -2.84
    '
    -2.55
    0
    -2.48
    亖
    -2.44
    毉
    -2.34
     ซึ่ง
    -2.30
     beberapa
    -2.23
     gewi
    -2.13
     pleg
    -2.06
    懵
    -2.06
    POSITIVE LOGITS
     Ironically
    2.48
    瓩
    2.39
    leggio
    2.39
    銪
    2.38
     resolute
    2.36
     größer
    2.36
     tireless
    2.31
     Traditionally
    2.30
     Surprisingly
    2.25
     Those
    2.23
    Activations Density 0.008%

    No Known Activations