© 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. 48223
    Prev
    Next
    INDEX
    Explanations

    happened in the past

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

    The neuron detects numeric tokens, especially measurements or counts expressed as integers or decimal values.

    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
     for
    -1.74
     from
    -1.55
     of
    -1.26
    么
    -1.13
    Il
    -1.09
     are
    -1.09
    apache
    -1.08
     GONNA
    -1.07
    \{\\
    -1.07
    НЫЙ
    -1.06
    POSITIVE LOGITS
     também
    1.45
     Также
    1.40
     также
    1.38
     your
    1.35
    también
    1.34
     religiosas
    1.31
    そも
    1.30
     también
    1.30
     också
    1.29
    視点
    1.24
    Activations Density 0.447%

    No Known Activations