© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33618
    Prev
    Next
    INDEX
    Explanations

    renowned, famous, prestigious entities

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

    The neuron is highly sensitive to numeric tokens (digit sequences) representing counts, years, amounts, or other quantitative values.

    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
     svého
    -0.99
    Viewport
    -0.95
    +++
    -0.92
    fication
    -0.91
    原始内容存档于
    -0.90
     мень
    -0.87
    preneur
    -0.85
    sels
    -0.85
     OnInit
    -0.84
    metries
    -0.84
    POSITIVE LOGITS
     renowned
    4.22
     famous
    3.84
     prominent
    3.59
     prestigious
    3.41
     respected
    3.31
    renowned
    3.11
     leading
    3.06
     reputable
    3.02
     eminent
    2.92
     reputed
    2.89
    Activations Density 0.227%

    No Known Activations