© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65593
    Prev
    Next
    INDEX
    Explanations

    file path declarations

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

    This neuron flags code-related context markers, such as indications of stack-trace file references or global scope variables.

    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
     for
    -2.31
     on
    -2.13
     this
    -2.09
     even
    -2.02
     with
    -2.02
     their
    -1.94
     and
    -1.94
     more
    -1.93
     it
    -1.91
     both
    -1.82
    POSITIVE LOGITS
     maniere
    2.03
     rigide
    1.86
     écrire
    1.59
     corriger
    1.55
    があり
    1.54
     EIGHT
    1.53
     murale
    1.52
    usually
    1.48
    THEY
    1.47
    primarily
    1.45
    Activations Density 0.000%

    No Known Activations