© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65280
    Prev
    Next
    INDEX
    Explanations

    for X [beneficiary/purpose]

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

    The neuron detects the “for” in general‐statement constructions like “it is important/desirable/imperative/appropriate for X to …,” i.e. phrases expressing necessity or desirability.

    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
     secado
    -1.70
    噤
    -1.64
     larges
    -1.57
     móveis
    -1.55
     colgantes
    -1.53
     profondeur
    -1.52
     drenaje
    -1.51
    はなく
    -1.51
     ausreich
    -1.50
     passende
    -1.49
    POSITIVE LOGITS
     to
    2.27
     for
    1.90
     one
    1.89
     will
    1.79
     two
    1.73
     if
    1.71
     by
    1.70
     and
    1.68
     three
    1.66
     you
    1.66
    Activations Density 0.013%

    No Known Activations