© 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. 112628
    Prev
    Next
    INDEX
    Explanations

    caring for

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

    The neuron fires on occurrences of the word “care” (and its inflected forms like caring, cares).

    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
    哢
    -3.34
    噚
    -2.75
    摃
    -2.75
     短发
    -2.53
     حاول
    -2.52
    啰
    -2.52
    枻
    -2.48
    ꦲ
    -2.44
    ющая
    -2.42
    cinogenicity
    -2.39
    POSITIVE LOGITS
    "
    3.36
    that
    2.67
    .
    2.59
    the
    2.44
    ness
    2.38
    those
    2.34
    AN
    2.33
    name
    2.31
    ،
    2.28
    месте
    2.25
    Activations Density 0.003%

    No Known Activations