© 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. 34-GEMMASCOPE-RES-131K
    7. 59038
    Prev
    Next
    INDEX
    Explanations

    clearing conditions

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

    The neuron responds to occurrences of the substring “clear” (as in clear, clearing, clearing-house, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     handling
    -1.16
     Handle
    -0.95
    handling
    -0.95
     handled
    -0.94
     Handling
    -0.93
     handle
    -0.91
     handles
    -0.88
    Handling
    -0.88
     HANDLE
    -0.83
    Handle
    -0.82
    POSITIVE LOGITS
    Introducing
    0.73
    去做
    0.70
     hinzu
    0.70
    活用
    0.68
     alun
    0.67
    Actualizar
    0.66
    رام
    0.65
     деталей
    0.65
     complica
    0.64
     Introducing
    0.63
    Activations Density 0.056%

    No Known Activations