© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66239
    Prev
    Next
    INDEX
    Explanations

    pose for

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

    This neuron detects the word “pose” (and its morphological variants like posed, poses, poseable) in contexts of people posing for photos or figures being poseable.

    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
    2
    -2.14
    ve
    -2.09
    OR
    -1.96
    _{
    -1.77
    就算
    -1.72
     ikke
    -1.71
    );
    -1.69
    https
    -1.67
    EN
    -1.66
    }}
    -1.64
    POSITIVE LOGITS
    擻
    1.85
    葑
    1.78
     ricas
    1.73
    櫪
    1.70
     IBOutlet
    1.68
    韁
    1.66
     tomado
    1.66
    烽
    1.61
    鑷
    1.61
    鼉
    1.60
    Activations Density 0.005%

    No Known Activations