© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103071
    Prev
    Next
    INDEX
    Explanations

    liquid flow and containment

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

    references to liquids or fluids, especially in technical or industrial contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    toir
    -0.86
    ensis
    -0.84
    大き
    -0.83
     marié
    -0.81
     кусо
    -0.81
     ilman
    -0.81
    newArray
    -0.81
     piezas
    -0.81
    aneous
    -0.80
     Cze
    -0.79
    POSITIVE LOGITS
     flowing
    2.05
     flowed
    1.76
     flows
    1.73
     flow
    1.73
     poured
    1.39
    flow
    1.28
     leaked
    1.20
     Flow
    1.20
     pooling
    1.19
    flowing
    1.18
    Activations Density 0.118%

    No Known Activations