© 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. 10-GEMMASCOPE-RES-131K
    4. 101672
    Prev
    Next
    INDEX
    Explanations

    entering states or modes

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

    The neuron detects expressions of entering or switching into a particular state or mode (e.g. “enter the job execution mode,” “go into defense mode against the cold,” “enters background”).

    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
     of
    -1.23
    </em>
    -1.13
    jącym
    -1.09
    érape
    -1.09
    ễn
    -1.08
    nuevos
    -1.07
     mesmas
    -1.06
     INFORMACIÓN
    -1.06
    Mitglieder
    -1.06
    这次
    -1.06
    POSITIVE LOGITS
    其他
    1.24
     dėl
    1.21
    Život
    1.19
    +}
    1.18
     {
    
    
    1.16
     zaradi
    1.15
     valgt
    1.15
     リップ
    1.15
    :],
    1.14
    日起
    1.13
    Activations Density 0.076%

    No Known Activations