© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1829
    Prev
    Next
    INDEX
    Explanations

    describing different sizes

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

    The neuron fires on mentions of “sizes,” i.e. tokens referring to dimensional or size specifications.

    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
     \
    -2.72
     to
    -2.69
     
    -2.67
    \
    -2.41
     For
    -2.41
    </td>
    -2.38
     verdaderamente
    -2.31
    '
    -2.20
    ↵↵
    -2.20
    it
    -2.16
    POSITIVE LOGITS
    of
    2.72
     sizes
    2.72
    ."
    2.58
    sizes
    2.50
    atief
    2.45
    喜欢的
    2.31
     fabricants
    2.30
    豨
    2.27
     acheteurs
    2.23
    癭
    2.19
    Activations Density 0.010%

    No Known Activations