© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3681
    Prev
    Next
    INDEX
    Explanations

    detachable, removable, interchangeable parts

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

    The neuron detects mentions of components being removable or detachable.

    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
     still
    -1.59
     new
    -1.34
     best
    -1.27
     whose
    -1.24
     remained
    -1.23
     drzwi
    -1.21
     who
    -1.20
    𖥧
    -1.17
     =\
    -1.17
     weird
    -1.15
    POSITIVE LOGITS
    without
    1.43
    糁
    1.21
     anhänger
    1.16
     olika
    1.12
     determinado
    1.09
    easily
    1.09
     طرق
    1.09
    ૯
    1.09
    different
    1.08
     forskning
    1.08
    Activations Density 0.088%

    No Known Activations