© 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. 22-GEMMASCOPE-RES-131K
    7. 64460
    Prev
    Next
    INDEX
    Explanations

    text string quotes; name

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

    The neuron flags numeric literals or tokens containing digits (i.e. numbers in code or data).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     that
    -1.57
     such
    -1.38
     this
    -1.38
     more
    -1.20
     of
    -1.09
    :
    -1.08
     which
    -1.05
     better
    -1.02
     three
    -1.02
    )$_
    -1.00
    POSITIVE LOGITS
    そして
    1.40
     conster
    1.08
    Михаил
    1.02
     görd
    1.02
     parfü
    1.01
    Kalau
    0.99
    Biografía
    0.98
    アカウント
    0.96
    と思っています
    0.96
    ఱ
    0.96
    Activations Density 0.014%

    No Known Activations