© 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. 90106
    Prev
    Next
    INDEX
    Explanations

    Graph API, Facebook integrations

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

    The neuron activates on numeric tokens (strings of digits), e.g. IDs, query‐parameter values, and other number sequences.

    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
    Alerter
    -0.75
    Donut
    -0.75
    Aktual
    -0.75
     decided
    -0.71
    Mith
    -0.70
     Lord
    -0.68
    하기
    -0.68
    هایت
    -0.68
    Gabri
    -0.67
    办理
    -0.67
    POSITIVE LOGITS
    ruptedException
    0.87
    жений
    0.84
    drücken
    0.83
    pods
    0.81
    neous
    0.81
    vim
    0.80
     roupas
    0.80
    pared
    0.79
    UseVisualStyle
    0.79
     קו
    0.76
    Activations Density 0.015%

    No Known Activations