© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8791
    Prev
    Next
    INDEX
    Explanations

    sulfur compounds

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

    scientific and technical terminology.

    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
     Then
    -3.41
    [
    -2.55
    );
    -2.53
    ."
    -2.50
     This
    -2.50
     However
    -2.44
     Fortunately
    -2.42
     Therefore
    -2.36
     Dieses
    -2.34
    I
    -2.27
    POSITIVE LOGITS
    鱨
    2.84
    苁
    2.36
    螽
    2.30
     hundred
    2.28
     یا
    2.27
     —
    2.27
    噐
    2.25
    继续
    2.22
    她的
    2.19
    槼
    2.17
    Activations Density 0.023%

    No Known Activations