© 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. 22-GEMMASCOPE-RES-131K
    7. 66814
    Prev
    Next
    INDEX
    Explanations

    heat treatment and storage conditions

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

    terms related to thermal processing in scientific contexts, especially annealing, calcination, and heating at specific temperatures.

    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_22/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
    ¹.
    -1.30
     alugar
    -1.23
     способствует
    -1.23
    そもそも
    -1.18
     juſt
    -1.17
    ;
    -1.17
    PhysRevLett
    -1.11
     Shetterly
    -1.11
     offrir
    -1.10
     SEDS
    -1.09
    POSITIVE LOGITS
     at
    1.94
     after
    1.93
     to
    1.91
     on
    1.84
     in
    1.76
     before
    1.73
     or
    1.66
     atriz
    1.45
     afterwards
    1.39
     during
    1.37
    Activations Density 0.115%

    No Known Activations