© 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. 115711
    Prev
    Next
    INDEX
    Explanations

    `self` followed by method

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

    The neuron fires strongly on tokens that consist of numeric characters, 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
     off
    -0.72
    工場
    -0.68
     Travers
    -0.65
    дцать
    -0.65
     nessa
    -0.65
    photon
    -0.65
    ואר
    -0.65
     کاب
    -0.63
    روید
    -0.63
    からも
    -0.63
    POSITIVE LOGITS
     Github
    0.75
    aat
    0.67
    utsch
    0.66
     Chad
    0.66
    味噌
    0.65
    semitism
    0.65
    ümer
    0.65
    esper
    0.65
    不断
    0.63
     VIN
    0.63
    Activations Density 0.059%

    No Known Activations