© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65806
    Prev
    Next
    INDEX
    Explanations

    state of being idle

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

    The main thing this neuron does is detect references to an idle or standby state (e.g., device idle times or standby modes).

    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
     startling
    -0.96
     отдела
    -0.95
    这下
    -0.95
     avaliar
    -0.95
     liberdade
    -0.92
    锨
    -0.91
     dezen
    -0.91
     ベージュ
    -0.90
     reconnaître
    -0.89
     relentless
    -0.89
    POSITIVE LOGITS
     idle
    1.09
     Since
    1.06
    While
    1.00
     Idle
    0.99
     chatter
    0.98
     While
    0.97
     Although
    0.96
     For
    0.96
    IDLE
    0.95
    Since
    0.95
    Activations Density 0.005%

    No Known Activations