© 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. 15465
    Prev
    Next
    INDEX
    Explanations

    programming code declarations

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

    The neuron is chiefly responding to runs of whitespace (indentation) in the source text.

    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
     balcón
    -1.28
    谙
    -1.27
    ngths
    -1.27
    création
    -1.27
     herein
    -1.21
    ptos
    -1.19
    dients
    -1.19
    cians
    -1.18
     misiones
    -1.18
    phem
    -1.17
    POSITIVE LOGITS
     teka
    1.36
     both
    1.24
     meste
    1.23
     rosse
    1.22
     juta
    1.18
     cento
    1.18
    这样的
    1.16
     alun
    1.13
     tull
    1.13
     geografia
    1.11
    Activations Density 0.016%

    No Known Activations