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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95615
    Prev
    Next
    INDEX
    Explanations

    years ranges

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

    The neuron strongly activates on en‐dashes or hyphens used in date and number ranges (e.g. “1952–57” or “–1960”).

    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
     which
    -1.30
     whose
    -1.28
     as
    -1.27
     any
    -1.16
     at
    -1.16
     using
    -1.16
     spurred
    -1.09
     used
    -1.08
     with
    -1.06
     unique
    -1.06
    POSITIVE LOGITS
     AMAZING
    1.20
     soooo
    1.15
     sooo
    1.12
    ほとん
    1.08
    UNICIP
    1.05
    allows
    1.04
    bbie
    1.03
     компания
    1.02
     alcune
    1.02
     alcuni
    1.02
    Activations Density 0.021%

    No Known Activations