© 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. 45290
    Prev
    Next
    INDEX
    Explanations

    urged to take action

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

    The neuron detects exhortative or directive language—phrases where someone is urging, calling on, or advising others to do something.

    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
     both
    -1.87
     When
    -1.75
     many
    -1.66
     but
    -1.65
     each
    -1.63
     with
    -1.63
     multifaceted
    -1.61
     superbly
    -1.55
     them
    -1.53
     Going
    -1.53
    POSITIVE LOGITS
     بينما
    1.61
    馓
    1.60
     ausreichend
    1.57
    鸸
    1.55
     новую
    1.55
     行き
    1.54
     spearheaded
    1.53
     !!!!!
    1.51
    螃
    1.50
     !!!!
    1.49
    Activations Density 0.016%

    No Known Activations