© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176828
    Prev
    Next
    INDEX
    Explanations

    story about

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

    yogurt or ChatGPT responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    예
    0.53
    ان
    0.50
    各
    0.49
    কা
    0.48
     Wast
    0.47
    adecimal
    0.47
    дон
    0.46
    주고
    0.46
    اه
    0.46
     kwa
    0.45
    POSITIVE LOGITS
     respostas
    0.54
    abhavena
    0.49
     resposta
    0.46
    ungee
    0.46
    তীর্থ
    0.46
    ]]->
    0.45
     respuesta
    0.44
     CENTER
    0.44
     pescado
    0.44
     walkable
    0.44
    Activations Density 0.002%

    No Known Activations