© 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. 39855
    Prev
    Next
    INDEX
    Explanations

    material curing

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

    The neuron is detecting mentions of “cure” and its variants (e.g. cure, curing, cured).

    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
    ৢ
    -3.09
    ⢅
    -3.09
    苙
    -2.97
    ⢪
    -2.78
    ⎆
    -2.72
    輒
    -2.55
    秶
    -2.55
     he
    -2.55
    
    -2.53
    ౧
    -2.50
    POSITIVE LOGITS
    h
    3.14
    r
    2.80
    e
    2.77
    These
    2.55
    They
    2.52
    y
    2.33
    This
    2.20
    AS
    2.14
    just
    2.13
     He
    2.11
    Activations Density 0.006%

    No Known Activations