© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60049
    Prev
    Next
    INDEX
    Explanations

    ready

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

    The neuron fires strongly on instances of the word “ready.”

    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
    O
    -2.69
    ma
    -2.48
     $
    -2.44
    m
    -2.41
     i
    -2.41
     dando
    -2.41
     két
    -2.36
    te
    -2.34
     wcześ
    -2.34
    ty
    -2.33
    POSITIVE LOGITS
    ･･
    2.89
    風格
    2.50
    This
    2.45
     ataupun
    2.44
    These
    2.42
    Probably
    2.36
    Before
    2.34
     現貨
    2.34
    Despite
    2.34
    Although
    2.33
    Activations Density 0.008%

    No Known Activations