© 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. 22-GEMMASCOPE-RES-131K
    7. 84369
    Prev
    Next
    INDEX
    Explanations

    regions and security

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

    The neuron activates on numeric tokens (digits and numbers) in the 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_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
    Ї
    -0.99
     みんな
    -0.85
    дым
    -0.80
     piccoli
    -0.78
    ણી
    -0.77
     двигатель
    -0.77
     ristor
    -0.77
    inkite
    -0.77
     Mukherjee
    -0.76
    OSO
    -0.76
    POSITIVE LOGITS
    ദ്
    0.86
    機種
    0.82
    ('/:
    0.82
    </em>
    0.80
    Mimi
    0.79
    ]")]
    0.77
    wissenschaften
    0.76
    şk
    0.75
    opathy
    0.75
    åringen
    0.73
    Activations Density 0.034%

    No Known Activations