© 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. 34-GEMMASCOPE-RES-131K
    4. 33573
    Prev
    Next
    INDEX
    Explanations

    citation

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

    The neuron primarily detects numeric tokens (integer literals or other digit-only 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_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
    VALUES
    -0.75
    izade
    -0.71
     פי
    -0.69
    Vox
    -0.68
     kämp
    -0.68
    CHOICE
    -0.68
     erfolgreich
    -0.67
    twimg
    -0.67
     пода
    -0.66
     eve
    -0.65
    POSITIVE LOGITS
    orodos
    0.77
     Negra
    0.73
    roidered
    0.69
     Bassett
    0.68
     proč
    0.67
     diha
    0.67
    semaphore
    0.65
     Staging
    0.65
    mess
    0.65
     тока
    0.65
    Activations Density 0.041%

    No Known Activations