© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67197
    Prev
    Next
    INDEX
    Explanations

    stdafx.h

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

    The neuron tends to light up on relatively uncommon or less frequent words.

    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
     ſch
    -3.53
     parachoque
    -3.47
     sprüche
    -3.38
    羮
    -3.16
    
    -3.13
    檮
    -3.13
    鱚
    -3.02
    齜
    -3.00
    哢
    -2.98
    余談
    -2.97
    POSITIVE LOGITS
    "
    4.13
    .(
    3.14
    (
    3.09
    ."
    3.06
     or
    3.05
     is
    2.94
     (
    2.81
     就
    2.80
    [
    2.75
    ),
    2.73
    Activations Density 0.029%

    No Known Activations