© 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. 64376
    Prev
    Next
    INDEX
    Explanations

    2

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

    The neuron activates on standalone numeric tokens (digits or multi‐digit numbers), i.e. it’s looking for numbers.

    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
     while
    -1.05
     because
    -1.00
     on
    -0.98
    These
    -0.91
     There
    -0.91
     or
    -0.91
     allows
    -0.88
     offered
    -0.84
     first
    -0.84
     received
    -0.84
    POSITIVE LOGITS
     Atención
    0.96
     kooper
    0.96
     comprenant
    0.94
     circons
    0.93
    TREATMENT
    0.92
     rafting
    0.92
    oad
    0.92
     fosfor
    0.91
     UPDATE
    0.87
     supplé
    0.87
    Activations Density 0.002%

    No Known Activations