© 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. 98751
    Prev
    Next
    INDEX
    Explanations

    system states like Ended, Incoming, Active

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

    The neuron fires on tokens naming program or system states or events (e.g. “End,” “Ended,” “CONNECTING,” “DISCONNECTED,” 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
    孩子的
    -0.89
     svoj
    -0.86
    Executed
    -0.83
     disappro
    -0.82
     субъек
    -0.79
    かなかった
    -0.79
     ancora
    -0.79
    Expire
    -0.77
     była
    -0.76
    ガジン
    -0.76
    POSITIVE LOGITS
     idle
    1.62
    idle
    1.48
     waiting
    1.32
     Idle
    1.22
     ready
    1.19
    Idle
    1.13
    ready
    1.13
    WaitFor
    1.12
    MessageState
    1.09
     wait
    1.09
    Activations Density 0.022%

    No Known Activations