© 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. 34-GEMMASCOPE-RES-131K
    7. 49267
    Prev
    Next
    INDEX
    Explanations

    method calls or object instantiation

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

    The neuron is strongly activated by user-defined identifiers in code (e.g. variable, parameter, and function 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_34/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
     for
    -1.63
     so
    -1.36
     these
    -1.34
     others
    -1.26
     even
    -1.20
     didn
    -1.19
     other
    -1.18
     at
    -1.13
     from
    -1.12
     therefore
    -1.11
    POSITIVE LOGITS
    、「
    1.22
    false
    1.13
    任何
    1.10
     impecable
    1.09
    ，“
    1.09
     custa
    1.06
    、《
    1.04
     gustar
    1.04
     false
    1.02
    _________
    1.02
    Activations Density 0.024%

    No Known Activations