© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 38809
    Prev
    Next
    INDEX
    Explanations

    count on

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

    The neuron fires on phrasal-verb constructions where a verb is immediately followed by “on” (e.g. “count on,” “rely on,” “depend on”).

    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
    颔
    -1.94
     europeo
    -1.81
     Когда
    -1.80
    之後
    -1.77
    if
    -1.71
    ⡪
    -1.66
     creando
    -1.66
     treating
    -1.65
     используют
    -1.63
     communicating
    -1.60
    POSITIVE LOGITS
    al
    1.78
    们的
    1.63
    ur
    1.63
    ته
    1.59
    an
    1.59
    𓆝
    1.58
    ₁)
    1.58
    >
    
    1.55
     bijvoorbeeld
    1.55
    纾
    1.50
    Activations Density 0.004%

    No Known Activations