© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75345
    Prev
    Next
    INDEX
    Explanations

    assembly and lists

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

    The neuron strongly activates on numeric tokens (immediate constants and 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
    }
    -1.82
    p
    -1.71
    even
    -1.65
    e
    -1.65
    us
    -1.62
    Its
    -1.59
    它的
    -1.58
    ta
    -1.54
     staten
    -1.54
    ri
    -1.52
    POSITIVE LOGITS
     from
    1.75
     the
    1.70
    bloomberg
    1.66
    tvguide
    1.53
     Abenteuer
    1.49
    berserk
    1.48
     gutem
    1.47
    batik
    1.45
    olkata
    1.45
    mpagne
    1.45
    Activations Density 0.008%

    No Known Activations