© 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. 34-GEMMASCOPE-RES-131K
    7. 78608
    Prev
    Next
    INDEX
    Explanations

    user roles and status

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

    The neuron fires on numeric literals (sequences of digits) in code or text.

    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
    quien
    -0.98
    mensch
    -0.91
     informací
    -0.90
     délicieux
    -0.87
    credential
    -0.86
     velikost
    -0.84
    prá
    -0.82
     ਗ
    -0.81
     adolescente
    -0.81
     людей
    -0.80
    POSITIVE LOGITS
     ordinary
    1.55
    普通
    1.41
     member
    1.30
     regular
    1.28
     guest
    1.25
     manager
    1.20
     normal
    1.20
     普通
    1.16
     user
    1.16
    ordinary
    1.15
    Activations Density 0.022%

    No Known Activations