© 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. 29140
    Prev
    Next
    INDEX
    Explanations

    Ha, haha, like

    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_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
     étrangers
    -1.73
    𓆜
    -1.61
    CA
    -1.59
    UR
    -1.51
    klare
    -1.48
    råd
    -1.45
    اشتی
    -1.44
    IR
    -1.43
     behandling
    -1.43
     asta
    -1.41
    POSITIVE LOGITS
     It
    1.46
    mathrm
    1.39
    cinnati
    1.37
    一根
    1.35
     erreich
    1.35
    <0xD5>
    1.33
    vellous
    1.30
     frecuentemente
    1.28
     Your
    1.26
    tabilidade
    1.26
    Activations Density 0.005%

    No Known Activations