© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129960
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and specifications

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

    The neuron detects highly technical, domain-specific terminology describing cement and concrete chemistry and material properties.

    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
    chery
    -1.61
    谥
    -1.56
     concerne
    -1.48
    retten
    -1.45
    cribing
    -1.43
    ಝ
    -1.43
    Добавлено
    -1.42
     necessari
    -1.42
    mands
    -1.41
    ynchronously
    -1.39
    POSITIVE LOGITS
     of
    1.58
     if
    1.44
     etc
    1.40
     neuen
    1.38
     is
    1.32
     the
    1.28
     should
    1.26
     type
    1.23
     characteristics
    1.21
     sfondo
    1.19
    Activations Density 0.078%

    No Known Activations