© 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. 129121
    Prev
    Next
    INDEX
    Explanations

    clover, hedgehog, melon

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

    The neuron fires on names of organisms (plants or animals), e.g. “clover” and “hedgehog.”

    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
     使っ
    -2.67
    "-
    -2.52
    '(
    -2.38
    锨
    -2.33
    "(
    -2.30
    摭
    -2.28
    婼
    -2.23
    )."
    -2.23
    "...
    -2.22
    }}\
    -2.20
    POSITIVE LOGITS
    r
    2.94
    3
    2.64
    '
    2.42
    </h3>
    2.42
    —“
    2.34
    4
    2.33
     “
    2.33
    )
    2.31
    <bos>
    2.28
    there
    2.25
    Activations Density 0.004%

    No Known Activations