© 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. 8075
    Prev
    Next
    INDEX
    Explanations

    oneshot, oneside, onesymb

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

    The neuron fires on occurrences of the sequence “ones” (i.e. it detects the substring “ones”).

    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
    0
    -2.94
     heo
    -2.13
     was
    -2.06
    涐
    -2.06
    パフォーマンス
    -2.03
     graden
    -1.96
    >
    -1.95
     knop
    -1.95
     pary
    -1.95
    一样的
    -1.91
    POSITIVE LOGITS
    "
    2.44
    replyreport
    2.22
    служба
    2.20
    塤
    2.17
     Persön
    2.13
    
    2.11
     cripple
    2.09
    труд
    2.09
     acquaint
    2.08
    matically
    1.95
    Activations Density 0.005%

    No Known Activations