© 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. 34-GEMMASCOPE-RES-131K
    7. 735
    Prev
    Next
    INDEX
    Explanations

    numbers and specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Profess
    -0.71
    sise
    -0.71
     drains
    -0.71
    зировать
    -0.71
    Modi
    -0.70
     получить
    -0.70
     Quezon
    -0.69
    nalités
    -0.68
     palk
    -0.68
    neur
    -0.68
    POSITIVE LOGITS
     выгля
    0.77
     indices
    0.74
    Alexa
    0.71
    ovac
    0.71
    さんへ
    0.71
     felt
    0.69
     refuted
    0.68
    roads
    0.67
     glimp
    0.66
     Alexa
    0.66
    Activations Density 0.023%

    No Known Activations