© 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. 75422
    Prev
    Next
    INDEX
    Explanations

    trained personnel and animals

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ⟞
    -2.94
    考虑到
    -2.66
    蠃
    -2.63
     \
    -2.63
    没办法
    -2.50
     waarschijnlijk
    -2.42
     несмотря
    -2.28
    辚
    -2.23
     سایر
    -2.22
     wodurch
    -2.22
    POSITIVE LOGITS
    是
    3.20
    It
    3.19
    If
    3.06
    of
    2.70
     trained
    2.58
    時間
    2.47
     設備
    2.42
     meriva
    2.38
    Whether
    2.38
    in
    2.38
    Activations Density 0.007%

    No Known Activations