© 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. 111949
    Prev
    Next
    INDEX
    Explanations

    software test definitions

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

    class names in code, particularly those related to testing frameworks and base classes like "Component", "TestCase", "TestBase", and "Service".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on capitalized identifiers in source code, i.e. class, interface, module, or type names.

    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
    sel
    -1.43
    *
    -1.42
     into
    -1.41
    ad
    -1.38
    ten
    -1.36
    in
    -1.32
     Sometimes
    -1.30
     में
    -1.28
    os
    -1.26
    met
    -1.25
    POSITIVE LOGITS
     that
    2.59
     this
    1.84
     you
    1.61
     tohoto
    1.53
     ocupado
    1.45
     dře
    1.45
     like
    1.44
     azonban
    1.41
     naszych
    1.41
    却又
    1.38
    Activations Density 0.126%

    No Known Activations