© 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. 73865
    Prev
    Next
    INDEX
    Explanations

    heart beats

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

    The neuron detects mentions of "heart" as a physical or emotional center, particularly in emotional or sentimental contexts.

    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
    蒟
    -1.54
    зации
    -1.51
    рования
    -1.48
    蒡
    -1.47
    引言
    -1.44
    𞤢
    -1.42
    чении
    -1.41
    mitive
    -1.41
     bencana
    -1.41
    팎
    -1.39
    POSITIVE LOGITS
    憷
    1.61
    }
    1.61
    e
    1.55
    
    1.55
    -
    1.55
    怎
    1.53
    とりあえず
    1.52
     встречи
    1.51
    $,
    1.50
    揾
    1.46
    Activations Density 0.008%

    No Known Activations