© 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. 34-GEMMASCOPE-RES-131K
    7. 53896
    Prev
    Next
    INDEX
    Explanations

    yay or nay

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

    This neuron activates on numeric tokens (digits or number‐like strings, especially years and other numbers).

    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
    adina
    -0.73
    BirthDate
    -0.72
     glob
    -0.72
     nargin
    -0.70
     SEMESTER
    -0.70
    Біографія
    -0.70
    镜头
    -0.69
    Utiliz
    -0.69
     derrot
    -0.69
     Aguilera
    -0.68
    POSITIVE LOGITS
    tay
    1.46
    gay
    1.44
    ay
    1.42
    ray
    1.40
    AY
    1.38
     decay
    1.37
    hay
    1.34
     bay
    1.31
    Fay
    1.30
     Fay
    1.30
    Activations Density 0.040%

    No Known Activations