© 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. 34-GEMMASCOPE-RES-131K
    4. 6885
    Prev
    Next
    INDEX
    Explanations

    raise awareness or funds

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

    The neuron strongly activates on occurrences of the verb “raise” (including its morphological variants like “raising” and “raised”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    bu
    -0.77
     vorder
    -0.75
    ;&
    -0.74
    deriv
    -0.73
    Bal
    -0.73
     Bal
    -0.73
    bal
    -0.73
     reigning
    -0.73
     说
    -0.73
     Bellevue
    -0.73
    POSITIVE LOGITS
     eyebrows
    2.19
     awareness
    1.64
    awareness
    1.41
     eyebrow
    1.32
     alarms
    1.31
    raise
    1.27
    Raising
    1.26
     funds
    1.24
    raised
    1.21
    Cain
    1.21
    Activations Density 0.029%

    No Known Activations