© 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. 34068
    Prev
    Next
    INDEX
    Explanations

    hugging, embracing, arms

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

    The neuron detects words describing close physical embraces or affectionate holding (e.g., hugging, holding, snuggling).

    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
     But
    -1.29
     time
    -1.17
     What
    -1.16
    es
    -1.13
    </strong>
    -1.12
     but
    -1.12
    at
    -1.09
    on
    -1.08
    which
    -1.07
     set
    -1.05
    POSITIVE LOGITS
     capteur
    1.44
     gitar
    1.18
    蕺
    1.15
    ྃ
    1.13
    ingtones
    1.13
    Railway
    1.09
     POSITION
    1.09
     organisme
    1.08
     cinto
    1.07
    绻
    1.06
    Activations Density 0.010%

    No Known Activations