© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70418
    Prev
    Next
    INDEX
    Explanations

    added, installed, replaced, and improvements

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

    This neuron detects numeric expressions or measurement values (e.g. digits, decimals, 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_10/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
     their
    -1.41
    /
    -1.33
     others
    -1.33
    they
    -1.27
    お互
    -1.26
    ·
    -1.25
    この日
    -1.23
     ciertas
    -1.23
    these
    -1.22
    昨日は
    -1.22
    POSITIVE LOGITS
     then
    1.33
     mengubah
    1.32
    estones
    1.31
    ÈNE
    1.29
    kanie
    1.27
    ｙ
    1.27
    年から
    1.26
     afgelopen
    1.26
    nino
    1.24
    郿
    1.24
    Activations Density 0.066%

    No Known Activations