© 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. 11145
    Prev
    Next
    INDEX
    Explanations

    not to mention/be/worry

    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
     what
    -1.98
     plongée
    -1.79
    诸多
    -1.73
     arbeta
    -1.73
    谖
    -1.70
     akzeptieren
    -1.68
     our
    -1.66
    してみると
    -1.66
    创始
    -1.61
     bestäm
    -1.60
    POSITIVE LOGITS
     also
    1.84
     nowe
    1.55
     ofic
    1.54
     alſo
    1.51
     anu
    1.50
     gie
    1.48
    +}\
    1.48
    %",
    1.48
    __":
    1.46
    ↵
    1.45
    Activations Density 0.005%

    No Known Activations