© 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. 42045
    Prev
    Next
    INDEX
    Explanations

    basis sets, basis for, basis of

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

    This neuron fires on multi-digit numeric tokens.

    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
    哙
    -3.33
    歺
    -2.92
    齜
    -2.91
    behandling
    -2.67
    鋇
    -2.66
    铩
    -2.63
     considerados
    -2.55
     който
    -2.55
    珧
    -2.53
     proposons
    -2.50
    POSITIVE LOGITS
    in
    3.47
            
    3.13
    You
    3.09
    It
    2.95
    可以
    2.80
    A
    2.61
    This
    2.58
    Of
    2.58
    '
    2.56
    At
    2.55
    Activations Density 0.011%

    No Known Activations