© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    vibe or vibrio

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

    The neuron detects variations of the word "vibration" or "vibe", including references to musical vibrations, social atmospheres, and bacterial Vibrio species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    玧
    -2.83
    ↵
    -2.77
    ”:
    -2.69
     betreffenden
    -2.69
    閙
    -2.55
    ꯵
    -2.53
    ”;
    -2.50
     verwendeten
    -2.48
    鱻
    -2.48
    </h3>
    -2.39
    POSITIVE LOGITS
     
    2.47
     But
    2.33
    🗓
    2.19
    ,
    2.13
     Ва
    2.06
    茳
    2.05
     Чтобы
    1.97
     türk
    1.96
    .
    1.96
     istrinya
    1.95
    Activations Density 0.002%

    No Known Activations