© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70069
    Prev
    Next
    INDEX
    Explanations

    Credit or courtesy attributions

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

    The neuron is primarily triggered by decimal numbers (numeric values with a fractional part).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     You
    -1.58
     Words
    -1.45
    ३
    -1.41
     bestehende
    -1.40
     Medium
    -1.40
    0
    -1.38
     letzte
    -1.38
    هایی
    -1.37
     complicada
    -1.37
    1
    -1.36
    POSITIVE LOGITS
     of
    1.67
     masing
    1.39
    ньому
    1.38
    вини
    1.38
     tertentu
    1.37
    since
    1.36
    　　(
    1.36
    .
    1.30
     arī
    1.30
     indeb
    1.30
    Activations Density 0.014%

    No Known Activations