© 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. 115553
    Prev
    Next
    INDEX
    Explanations

    stepping down or aside

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

    The neuron detects words and forms related to stepping down or resigning (e.g. “step down,” “stepping down,” “stepped down,” “stood down,” “backed”).

    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
    eva
    -0.78
    冂
    -0.77
     magnum
    -0.76
    ющего
    -0.67
    テ
    -0.66
    iredo
    -0.63
    isse
    -0.63
     Mic
    -0.62
     しょう
    -0.62
    繆
    -0.62
    POSITIVE LOGITS
     down
    3.20
    Down
    2.36
    down
    2.33
     Down
    1.95
    DOWN
    1.84
     DOWN
    1.82
    ダウン
    1.64
     downed
    1.37
    downs
    1.30
     low
    1.30
    Activations Density 0.019%

    No Known Activations