© 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. 98274
    Prev
    Next
    INDEX
    Explanations

    Neuropsychologia and honours

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

    numbers (digit tokens), such as years, version numbers, or other numeric literals.

    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
    ).(
    -0.85
    celot
    -0.74
     چوبی
    -0.71
    škas
    -0.70
     Enchanted
    -0.70
     attributable
    -0.69
    瘩
    -0.67
    ].(
    -0.67
     Uhuru
    -0.66
    SWAP
    -0.65
    POSITIVE LOGITS
     sas
    0.71
     monet
    0.65
    まさかの
    0.62
    sas
    0.62
     celebrate
    0.62
    sedes
    0.62
    圣节
    0.61
    akas
    0.61
     afspraak
    0.61
    zilla
    0.61
    Activations Density 0.071%

    No Known Activations