© 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. 104291
    Prev
    Next
    INDEX
    Explanations

    identifying importance

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

    This neuron detects instances of the phrase “It is” (including its contraction “It’s”) introducing statements or recommendations.

    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
     from
    -1.70
    ítima
    -1.52
    彇
    -1.39
     soirée
    -1.36
     gari
    -1.34
    \%)
    -1.30
     "",
    -1.27
     on
    -1.27
     perjalanan
    -1.25
     caoutchouc
    -1.25
    POSITIVE LOGITS
     Comentarios
    1.45
    *
    1.41
     wszystkie
    1.40
     Hacer
    1.38
     we
    1.35
    يمكن
    1.35
    {
    1.34
    We
    1.34
     own
    1.33
     такую
    1.31
    Activations Density 0.064%

    No Known Activations