© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23498
    Prev
    Next
    INDEX
    Explanations

    permitted, provided, authorized, import

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

    The neuron strongly activates on numeric literals (e.g. scale factors, resolutions, version numbers) in code or configuration contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    blocks
    -0.82
     module
    -0.80
     LOW
    -0.77
     clerk
    -0.73
    žite
    -0.73
     Joh
    -0.72
     modules
    -0.70
    べし
    -0.70
    lini
    -0.69
     små
    -0.68
    POSITIVE LOGITS
     Augsburg
    0.69
    MF
    0.67
     Patrice
    0.66
    ैक
    0.64
    Jal
    0.62
    çak
    0.62
    Allocation
    0.61
    hage
    0.60
     입니다
    0.60
     Chet
    0.59
    Activations Density 0.080%

    No Known Activations