© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66942
    Prev
    Next
    INDEX
    Explanations

    width, red, modulus, June

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

    The neuron is mainly detecting numeric tokens (i.e. numbers and numerical values) in the 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_22/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
     germain
    -1.09
     trám
    -1.02
    גון
    -1.02
    ²/
    -1.00
    ³/
    -0.98
     tagit
    -0.96
    anstal
    -0.94
    !»
    -0.94
    ėjimo
    -0.93
    ˂
    -0.93
    POSITIVE LOGITS
     other
    1.44
     of
    1.19
     for
    1.18
     others
    1.09
     Other
    1.04
     just
    0.96
     інших
    0.93
     otro
    0.92
     Although
    0.91
     ursprünglich
    0.91
    Activations Density 0.018%

    No Known Activations