© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99418
    Prev
    Next
    INDEX
    Explanations

    signal, checkbox, triangle, echo

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

    The neuron fires on numeric measurement tokens (especially decimal numbers) and their associated technical terms in a signal‐processing circuit description.

    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
     this
    -2.78
     these
    -2.66
     there
    -1.91
     because
    -1.70
     when
    -1.58
     این
    -1.55
    はこの
    -1.53
     هذه
    -1.52
     they
    -1.44
     этому
    -1.43
    POSITIVE LOGITS
    *}\
    1.52
     volverá
    1.52
    只是一
    1.51
     остальных
    1.46
    好像是
    1.40
     высоты
    1.38
    Zubereitung
    1.35
    Significado
    1.34
    
    1.33
    }]{
    1.31
    Activations Density 0.727%

    No Known Activations