© 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. 112961
    Prev
    Next
    INDEX
    Explanations

    units of time and distance

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

    The neuron fires on numeric measurements—numbers immediately followed by unit tokens (e.g. “mi,” “km,” “min,” “sec,” “ft,” “yr”).

    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
    ’:
    -2.30
    ”),
    -2.27
    =’
    -2.22
     obligación
    -2.20
     director
    -2.16
     ujedno
    -2.13
    )”
    -2.11
    觏
    -2.09
    
    -2.09
    ”:
    -2.08
    POSITIVE LOGITS
     '
    3.50
    .,
    2.83
    ?"
    2.67
    ",
    2.50
     "
    2.47
    "
    2.41
    --
    2.41
     ('
    2.38
    ',
    2.25
    ".
    2.19
    Activations Density 0.020%

    No Known Activations