© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45144
    Prev
    Next
    INDEX
    Explanations

    programming control flow statements

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

    The neuron fires on numeric literals (especially floating‐point numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     but
    -1.78
     creativos
    -1.67
     mengumumkan
    -1.51
     któ
    -1.48
     confirmó
    -1.45
     necesariamente
    -1.43
     reemplazar
    -1.43
                
    -1.43
     and
    -1.42
     menceritakan
    -1.40
    POSITIVE LOGITS
    t
    1.46
     (
    1.46
     that
    1.41
    т
    1.38
     this
    1.36
    ły
    1.24
     on
    1.23
    жения
    1.23
     such
    1.20
    filepath
    1.20
    Activations Density 0.009%

    No Known Activations