© 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. 22-GEMMASCOPE-RES-131K
    4. 70777
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    The neuron activates on numeric tokens (i.e. literal numbers or number-containing tokens).

    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
    օ
    -0.90
    それ
    -0.85
    とても
    -0.85
    都可以
    -0.85
     :"
    -0.84
     ın
    -0.84
    μιουργ
    -0.84
     يتم
    -0.84
     peering
    -0.84
     taget
    -0.83
    POSITIVE LOGITS
     November
    0.93
    epsfig
    0.84
     December
    0.83
     wykonane
    0.82
     Nachhal
    0.82
    を目指す
    0.82
     actualiza
    0.81
    phylaxis
    0.80
     récentes
    0.80
     вещества
    0.80
    Activations Density 0.159%

    No Known Activations