© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26666
    Prev
    Next
    INDEX
    Explanations

    future trends and predictions

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

    This neuron detects numeric references—years, list numbers, statistics, and other digits or numbered list headings.

    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
    können
    -1.24
     супру
    -1.22
    🛢
    -1.21
     wöch
    -1.20
    verhält
    -1.17
    artiges
    -1.17
    暧
    -1.16
     ſou
    -1.16
     sillas
    -1.15
    ándote
    -1.12
    POSITIVE LOGITS
     will
    2.03
     trends
    1.94
     continue
    1.82
     continues
    1.73
     continuing
    1.49
     continued
    1.49
     trend
    1.48
     Tenden
    1.48
     тенден
    1.42
     increasingly
    1.37
    Activations Density 0.026%

    No Known Activations