© 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. 14520
    Prev
    Next
    INDEX
    Explanations

    cartilage and malnutrition

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

    medical terms related to cartilage and malnutrition in scientific texts.

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

    The neuron selectively activates on occurrences of the word “cartilage” (including its morphological variants).

    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
    </h3>
    -2.95
    嵛
    -2.66
     lancar
    -2.59
    🌃
    -2.58
    ᥫ
    -2.55
    ㈫
    -2.53
    懨
    -2.47
    嗞
    -2.42
    sandália
    -2.41
    覲
    -2.39
    POSITIVE LOGITS
    </b>
    2.89
     --
    2.77
     —
    2.72
     They
    2.69
    可不是
    2.64
     is
    2.64
    0
    2.59
    on
    2.47
    就像是
    2.38
     så
    2.31
    Activations Density 0.014%

    No Known Activations