© 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. 67380
    Prev
    Next
    INDEX
    Explanations

    All use in source

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

    The neuron activates on numeric tokens (digit sequences) 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
     METRO
    -1.15
    ◾
    -1.11
     ORO
    -1.07
     certificat
    -1.03
     fluide
    -1.02
    ===============
    -1.02
     perjuangan
    -1.01
    inputText
    -1.00
    そういえば
    -1.00
    //-
    -1.00
    POSITIVE LOGITS
     estos
    1.19
     llena
    1.15
     этих
    1.08
     amazing
    1.08
     Estos
    1.01
     inmueble
    1.01
     Bemerkungen
    1.00
     diseñ
    0.97
     Einrichtungen
    0.96
    abriel
    0.94
    Activations Density 0.009%

    No Known Activations