© 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. 15103
    Prev
    Next
    INDEX
    Explanations

    data type conversion

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

    This neuron lights up on programming‐style tokens—especially code identifiers, numeric literals, and other code snippets.

    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
    Ā
    -1.08
     eaux
    -1.08
     bateria
    -1.06
     souple
    -1.06
     trigo
    -1.05
    阳台
    -1.03
     statut
    -1.02
     שלהם
    -1.02
     bains
    -1.02
     panneaux
    -1.02
    POSITIVE LOGITS
     from
    2.16
     conversion
    1.65
     can
    1.34
     converting
    1.30
     conversions
    1.29
     converted
    1.23
    conversion
    1.23
     convert
    1.21
     Conversion
    1.20
     other
    1.20
    Activations Density 0.032%

    No Known Activations