© 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. 97874
    Prev
    Next
    INDEX
    Explanations

    arrow icon

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

    The neuron fires on numeric tokens (numbers or number‐like strings) in code or markup (e.g. CSS values, HTML tags/classes containing digits).

    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
    Buttons
    -0.94
     Buttons
    -0.82
    Button
    -0.82
     sana
    -0.79
     buttons
    -0.79
     kontroll
    -0.75
    Instr
    -0.75
     norme
    -0.74
     Chuan
    -0.74
    ENTAL
    -0.73
    POSITIVE LOGITS
     downward
    0.98
     arrow
    0.95
    caret
    0.90
    geer
    0.82
    ایی
    0.82
    temuan
    0.82
    vení
    0.82
    arrow
    0.81
    ape
    0.80
    triangle
    0.80
    Activations Density 0.004%

    No Known Activations