© 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. 70181
    Prev
    Next
    INDEX
    Explanations

    solid content and direction

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

    The neuron is specialized in detecting numeric and measurement-related tokens (e.g. digits, units, and quantitative terms).

    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
     allotments
    -0.71
     incipient
    -0.69
    dente
    -0.68
     кӀош
    -0.67
    FileReader
    -0.66
     Campground
    -0.66
     chuột
    -0.66
    奖
    -0.66
     Amplitude
    -0.65
     tubers
    -0.64
    POSITIVE LOGITS
     solid
    3.14
    solid
    2.88
    Solid
    2.83
     Solid
    2.73
     solids
    2.69
    SOLID
    2.16
     Solids
    2.16
     SOLID
    2.08
    solids
    1.91
     sólidos
    1.77
    Activations Density 0.054%

    No Known Activations