© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21039
    Prev
    Next
    INDEX
    Explanations

    flexible arrangements, access, or planning

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

    The neuron strongly activates on the word “flexible” (and its close semantic variants), marking instances of flexibility or adaptability.

    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
    􀂃
    -1.92
    喼
    -1.71
    鏐
    -1.69
    ܜ
    -1.66
    隨著
    -1.63
     unangemess
    -1.62
    籏
    -1.61
     ingredienti
    -1.60
    они
    -1.60
     Væ
    -1.59
    POSITIVE LOGITS
    on
    2.17
     was
    2.05
    x
    1.98
    g
    1.95
    ."
    1.94
    by
    1.88
    ?"
    1.86
    You
    1.77
    U
    1.76
    i
    1.73
    Activations Density 0.020%

    No Known Activations