© 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. 98885
    Prev
    Next
    INDEX
    Explanations

    thermodynamics and internal states

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

    scientific and mathematical concepts in academic or technical texts.

    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
     financeiro
    -0.94
     aján
    -0.76
     Δ
    -0.75
     хиру
    -0.73
    ungere
    -0.73
     Damascus
    -0.72
    調味料
    -0.71
     sözler
    -0.70
     ADO
    -0.70
     Kuwa
    -0.70
    POSITIVE LOGITS
     internal
    1.74
     Internal
    1.44
    Internal
    1.42
    internal
    1.41
    INTERNAL
    1.17
     energy
    1.13
     INTERNAL
    1.11
     pressure
    0.97
     enthalpy
    0.96
     bels
    0.94
    Activations Density 0.019%

    No Known Activations