© 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. 22-GEMMASCOPE-RES-131K
    7. 34220
    Prev
    Next
    INDEX
    Explanations

    heart followed by rate,failure, land, or beats

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

    The word "heart" in various contexts, including anatomical references and metaphorical uses.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the word “heart” (and related cardiac references).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    栳
    -3.16
    </sub>
    -2.78
    芣
    -2.50
     anteriormente
    -2.05
    詳しくは
    -2.03
    メガネ
    -2.02
    栒
    -2.02
    </h3>
    -2.02
    の方は
    -2.00
     ボーダー
    -2.00
    POSITIVE LOGITS
    鞴
    2.69
    膂
    2.55
    }
    2.53
    an
    2.28
    鹟
    2.22
     видит
    2.20
     kupić
    2.20
    件事情
    2.19
    ebenarnya
    2.19
    ('/');
    2.17
    Activations Density 0.033%

    No Known Activations