© 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. 25023
    Prev
    Next
    INDEX
    Explanations

    license text

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

    The neuron spikes on standalone numeric literals (integers or decimals) in the text.

    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
     with
    -1.42
     from
    -1.32
     without
    -1.20
     new
    -1.16
     nya
    -1.13
     måned
    -1.13
     to
    -1.12
     reise
    -1.10
     for
    -1.09
     sondern
    -1.08
    POSITIVE LOGITS
    indicated
    1.19
     idiotic
    1.18
    鴴
    1.13
    割と
    1.12
     vinte
    1.10
    きち
    1.10
    mainly
    1.10
    especially
    1.08
     exceptionally
    1.07
     EVEN
    1.07
    Activations Density 0.146%

    No Known Activations