© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70530
    Prev
    Next
    INDEX
    Explanations

    hope for future actions

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

    The neuron is triggered almost exclusively by occurrences of the token "to," i.e. the infinitive marker “to.”

    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
    㩒
    -1.52
     deberes
    -1.50
     jugado
    -1.47
     BOTH
    -1.47
    すすめ
    -1.46
     mejorado
    -1.46
    )_{
    -1.44
    過的
    -1.43
     которое
    -1.42
     variadas
    -1.42
    POSITIVE LOGITS
    *
    1.86
    an
    1.86
    [
    1.78
    )
    1.71
     be
    1.69
     see
    1.67
    4
    1.60
     able
    1.55
     
    1.54
    al
    1.53
    Activations Density 0.009%

    No Known Activations