© 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. 10-GEMMASCOPE-RES-131K
    7. 87145
    Prev
    Next
    INDEX
    Explanations

    rodents

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

    references to rodents in scientific or medical research contexts.

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

    The neuron detects mentions of rodents (the word “rodent” or “rodents”).

    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
    ?”
    -2.88
    剮
    -2.52
    e
    -2.41
    ar
    -2.34
    ]
    -2.30
     [],
    -2.22
    ”
    -2.19
    d
    -2.19
     様子
    -2.17
    ”-
    -2.16
    POSITIVE LOGITS
    '
    3.03
    屃
    2.80
    ſelf
    2.33
    鸶
    2.17
     utilizing
    2.14
    sonian
    2.13
     utilising
    2.11
     bezw
    2.06
    the
    2.05
     employing
    2.05
    Activations Density 0.002%

    No Known Activations