© 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. 34-GEMMASCOPE-RES-131K
    7. 30262
    Prev
    Next
    INDEX
    Explanations

    detecting changes or breaks

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

    The neuron activates on numerical tokens or numeric data (e.g. figures, statistics, ages, counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     continuant
    -0.76
     Arya
    -0.74
    dingen
    -0.72
     tableaux
    -0.71
     Thermodynamics
    -0.70
     Complementary
    -0.70
    進
    -0.70
     DINNER
    -0.69
     Zion
    -0.68
    Wr
    -0.68
    POSITIVE LOGITS
     change
    1.29
     regime
    1.25
     abrupt
    1.23
     break
    1.20
     breakpoint
    1.17
     Break
    1.13
     Change
    1.10
    Change
    1.08
     breaks
    1.07
    Break
    1.07
    Activations Density 0.032%

    No Known Activations