© 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. 22-GEMMASCOPE-RES-131K
    7. 66392
    Prev
    Next
    INDEX
    Explanations

    sensitive first second

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

    The neuron flags tokens in comma‐separated enumerations (i.e. items in lists).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     läh
    -0.88
    事儿
    -0.85
     sorgen
    -0.85
    addContainerGap
    -0.82
    Karakteristik
    -0.77
    soit
    -0.75
    Новые
    -0.74
    ieme
    -0.73
     clinic
    -0.73
    ඒ
    -0.73
    POSITIVE LOGITS
     pause
    1.33
     followed
    1.29
     paused
    1.16
     промежу
    1.13
     between
    1.11
    pause
    1.10
     中
    1.09
     gap
    1.05
    Pause
    1.02
     suivie
    0.98
    Activations Density 0.137%

    No Known Activations