© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43178
    Prev
    Next
    INDEX
    Explanations

    reinforce or strengthen

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

    The neuron fires on verbs (and their inflected forms) that mean “to reinforce” or “to strengthen.”

    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
    璈
    -1.95
     tingkat
    -1.83
    ähkö
    -1.81
     رائع
    -1.66
    excess
    -1.66
    🕗
    -1.62
    ',
    -1.61
    ⸫
    -1.60
     tất
    -1.59
     飲
    -1.56
    POSITIVE LOGITS
    >
    1.98
     of
    1.79
     ersten
    1.76
     durch
    1.65
    はこの
    1.60
    }
    1.53
    f
    1.51
     fondateur
    1.45
    missão
    1.45
    водить
    1.44
    Activations Density 0.021%

    No Known Activations