© 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. 10-GEMMASCOPE-RES-131K
    7. 104448
    Prev
    Next
    INDEX
    Explanations

    deciduous, peroxidase, TableCell

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

    scientific or technical terms related to biology, especially terms like "peroxidase," "deciduous," and "cell" in biological 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_10/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
    ’，
    -3.14
    窿
    -2.59
    埽
    -2.44
    ࿆
    -2.34
    锵
    -2.33
    grandmother
    -2.28
    癀
    -2.28
    𝟭
    -2.27
    嵛
    -2.27
    噲
    -2.25
    POSITIVE LOGITS
     bewilder
    3.41
    *
    3.11
    }\
    2.48
    ۔
    2.47
    c
    2.45
     \
    2.42
     capricious
    2.39
     circumvent
    2.38
     sullen
    2.36
     ſol
    2.34
    Activations Density 0.016%

    No Known Activations