© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20984
    Prev
    Next
    INDEX
    Explanations

    announcing new information

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

    The neuron fires strongly on the contiguous substring “Now” (i.e. the token “Now” or any token containing “Now”).

    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
     และ
    -2.78
    鲩
    -2.75
     poderosos
    -2.70
     három
    -2.48
    genodigd
    -2.45
     paździer
    -2.42
    ඈ
    -2.42
    那种
    -2.42
    "
    -2.38
    ݮ
    -2.38
    POSITIVE LOGITS
     Now
    2.83
    寕
    2.80
    e
    2.73
     was
    2.69
    a
    2.63
    琹
    2.58
    胧
    2.55
    镦
    2.53
    ed
    2.45
    ！！”
    2.41
    Activations Density 0.013%

    No Known Activations