© 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. 67472
    Prev
    Next
    INDEX
    Explanations

    Bohemian culture and lifestyles

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

    The neuron detects mentions of the “bohemian” aesthetic (e.g. “bohemian,” “boho,” “vibe”).

    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
    ギュア
    -2.98
    
    -2.89
    秶
    -2.80
     ſch
    -2.77
    をしていた
    -2.67
     間取り
    -2.55
     Reſ
    -2.53
     feltro
    -2.53
     uſed
    -2.50
    􀂃
    -2.45
    POSITIVE LOGITS
    {
    3.64
    L
    3.11
    </b>
    2.91
    }$
    2.84
    (
    2.83
    –
    2.80
    .
    2.75
    %
    2.67
    M
    2.63
    ”
    2.58
    Activations Density 0.004%

    No Known Activations