© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98865
    Prev
    Next
    INDEX
    Explanations

    Mitt Romney

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

    This neuron responds strongly to the Japanese hiragana sequence “がんばって,” i.e. that informal encouragement phrase.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    on
    -3.41
    st
    -3.02
    ."
    -2.89
    e
    -2.84
    了很多
    -2.77
    饪
    -2.72
    }$
    -2.52
    葙
    -2.52
    c
    -2.48
    ay
    -2.44
    POSITIVE LOGITS
    应该
    2.50
    ◔
    2.44
    .”
    2.38
    
    2.31
     сеть
    2.28
    嵓
    2.28
    ,’
    2.25
     戰
    2.22
    ουργ
    2.19
    nitř
    2.17
    Activations Density 0.005%

    No Known Activations