© 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. 70900
    Prev
    Next
    INDEX
    Explanations

    Oxidative stress

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

    numerical values in a document, particularly when they appear in dates, times, or measurements.

    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
     inconvénients
    -1.45
     vertus
    -1.25
    Furthermore
    -1.24
    Readers
    -1.22
    ølge
    -1.20
    Moreover
    -1.20
    ଵ
    -1.20
     sekaligus
    -1.18
    Additionally
    -1.17
     méret
    -1.17
    POSITIVE LOGITS
     estrema
    1.41
     says
    1.36
     doesn
    1.35
     there
    1.27
     diversa
    1.26
     distintas
    1.24
     it
    1.23
     said
    1.20
     different
    1.19
     считается
    1.18
    Activations Density 0.000%

    No Known Activations