© 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. 13757
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers

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

    The neuron activates strongly on numeric tokens or numeric literals (i.e. sequences of digits).

    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
     scelto
    -0.88
     lasciare
    -0.87
     módulos
    -0.85
     iniziare
    -0.81
     continue
    -0.80
    というと
    -0.79
     posteriores
    -0.79
    viaf
    -0.78
     forms
    -0.77
     rinnov
    -0.77
    POSITIVE LOGITS
     indirec
    0.92
    🅡
    0.92
    Παραπομπές
    0.90
    AVIA
    0.90
    мся
    0.89
     Medic
    0.86
    τικές
    0.85
    gfx
    0.85
    veien
    0.85
    rechnung
    0.80
    Activations Density 0.028%

    No Known Activations