© 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. 10-GEMMASCOPE-RES-131K
    7. 47635
    Prev
    Next
    INDEX
    Explanations

    as of date/time indicator

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

    The neuron fires on multi‐digit numeric tokens (including decimals), i.e. when it encounters a number of more than one digit.

    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
    </h2>
    -2.02
    the
    -2.00
    溦
    -2.00
    )$\\
    -2.00
    恐れ
    -1.99
    eddable
    -1.98
    さんが
    -1.98
    icznej
    -1.97
    勛
    -1.95
    énieurs
    -1.95
    POSITIVE LOGITS
    谖
    2.27
     et
    1.95
    ↵
    1.93
    er
    1.88
    s
    1.86
    “
    1.85
    en
    1.84
    '
    1.81
     you
    1.80
     teile
    1.80
    Activations Density 0.007%

    No Known Activations