© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7017
    Prev
    Next
    INDEX
    Explanations

    applies to

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

    The neuron is specialized in spotting floating‐point numeric tokens (numbers with decimal points).

    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
     into
    -1.97
     "
    -1.80
     '
    -1.78
    </b>
    -1.61
     is
    -1.58
     at
    -1.50
     $
    -1.45
     ‘
    -1.45
     $\
    -1.37
     as
    -1.34
    POSITIVE LOGITS
     you
    1.95
    镲
    1.88
    敺
    1.81
    providedIn
    1.76
    but
    1.63
     Minggu
    1.59
    ൎ
    1.56
     السعود
    1.56
    驁
    1.55
    .&
    1.50
    Activations Density 0.030%

    No Known Activations