© 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. 22-GEMMASCOPE-RES-131K
    7. 26861
    Prev
    Next
    INDEX
    Explanations

    SQL/code method calls

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

    The neuron detects code tokens corresponding to method or function calls (i.e. identifiers immediately followed by parentheses).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    がある
    -1.52
    などは
    -1.46
    があり
    -1.38
    1
    -1.34
    もあって
    -1.33
    が
    -1.32
    もありますが
    -1.28
    があって
    -1.28
    などを
    -1.26
    を持つ
    -1.18
    POSITIVE LOGITS
    It
    1.71
    There
    1.70
    This
    1.49
    What
    1.46
    You
    1.45
    અ
    1.45
    After
    1.44
    –
    1.43
    Every
    1.42
    That
    1.41
    Activations Density 0.007%

    No Known Activations