© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63300
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

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

    The neuron is activated by tokens containing numeric digits (i.e. it detects 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
    PageContext
    -0.71
    CAS
    -0.68
    าม
    -0.68
    전
    -0.66
     杏
    -0.66
    Rl
    -0.66
     село
    -0.66
    liebte
    -0.65
    eez
    -0.65
    itates
    -0.65
    POSITIVE LOGITS
    ASSOCI
    0.69
     suman
    0.69
     Cahill
    0.68
    끝
    0.68
     ता
    0.67
    arische
    0.66
    观念
    0.66
    TRAINING
    0.65
    oman
    0.65
     publique
    0.65
    Activations Density 0.052%

    No Known Activations