© 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. 22-GEMMASCOPE-RES-131K
    7. 39943
    Prev
    Next
    INDEX
    Explanations

    desperate searches and attempts

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

    The neuron activates on instances of the word “desperate” (and close variants) signaling extreme urgency or need.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    튿
    -2.69
    嚶
    -2.42
    扨
    -2.39
    zyj
    -2.34
    嘖
    -2.33
     sviluppo
    -2.33
    厹
    -2.33
    雱
    -2.30
    搥
    -2.28
    躡
    -2.23
    POSITIVE LOGITS
    0
    3.22
    ’
    3.05
    ”
    2.88
    ”,
    2.75
    .
    2.64
    ),
    2.27
    、
    2.20
    an
    2.19
    a
    2.16
     for
    2.13
    Activations Density 0.010%

    No Known Activations