© 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. 65210
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming languages

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

    The neuron fires on numeric tokens (e.g. execution counts, code-fence language markers, and other literal numbers).

    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
     This
    -1.45
    TRIBUTES
    -1.37
    𖥧
    -1.30
    जय
    -1.25
    всем
    -1.24
    ValueStyle
    -1.23
     parution
    -1.23
     quaint
    -1.23
    sistors
    -1.22
     soothe
    -1.21
    POSITIVE LOGITS
    .
    1.90
    8
    1.30
    3
    1.30
    5
    1.25
    0
    1.21
     verlangt
    1.20
    心灵
    1.19
     durabilidad
    1.19
    >
    1.16
     majority
    1.16
    Activations Density 0.000%

    No Known Activations