© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128406
    Prev
    Next
    INDEX
    Explanations

    thermoplastic material and polymers

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

    The neuron detects the word "thermoplastic" and related materials science terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     abbildung
    -2.34
     而
    -2.28
    这种
    -2.17
    毉
    -2.16
    が表示
    -2.11
    这个
    -2.09
     μπορεί
    -2.08
    賔
    -2.05
    It
    -2.05
     denominado
    -2.02
    POSITIVE LOGITS
    e
    2.64
    祼
    2.52
    otriva
    2.34
    扺
    2.33
    ⤥
    2.28
     является
    2.22
    section
    2.20
    啣
    2.20
    ised
    2.19
    接下来的
    2.19
    Activations Density 0.004%

    No Known Activations