© 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. 98020
    Prev
    Next
    INDEX
    Explanations

    preparing for something

    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
     permanecer
    -1.15
     aleación
    -1.10
     principalement
    -1.10
     progresses
    -1.08
    そりゃ
    -1.06
     proveniente
    -1.05
    ビックリ
    -1.05
     comprende
    -1.04
     puedo
    -1.00
     solidif
    -1.00
    POSITIVE LOGITS
     for
    2.33
     However
    1.25
     According
    1.23
     Prepare
    1.15
     a
    1.15
     пищи
    1.14
     to
    1.13
    wanzig
    1.12
    ustomed
    1.11
    المكان
    1.07
    Activations Density 0.021%

    No Known Activations