© 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. 8465
    Prev
    Next
    INDEX
    Explanations

    laminate materials

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

    This neuron activates on occurrences of “lamin”-based words (e.g., laminate/laminated/laminating).

    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
    6
    -2.78
    8
    -2.72
    7
    -2.70
    3
    -2.63
    2
    -2.59
     ส์
    -2.58
    9
    -2.56
    5
    -2.52
    "
    -2.47
     eatery
    -2.27
    POSITIVE LOGITS
     chiefly
    2.53
    </b>
    2.34
     mostly
    2.33
    ;
    2.27
     varied
    2.27
     both
    2.19
     primarily
    2.19
     意思
    2.14
     also
    2.11
    -”
    2.11
    Activations Density 0.002%

    No Known Activations