© 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. 112360
    Prev
    Next
    INDEX
    Explanations

    sufficiently/enough followed by descriptor

    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
     to
    -1.94
    compared
    -1.41
    either
    -1.41
    ＆
    -1.37
    both
    -1.34
    "}";
    -1.34
    ？
    -1.34
    
    -1.34
    {
    -1.30
    imply
    -1.27
    POSITIVE LOGITS
    关卡
    1.48
     號
    1.42
     costuras
    1.31
    пой
    1.29
     auch
    1.24
     說
    1.24
     Geografía
    1.20
    бо
    1.20
    PMG
    1.20
    heureusement
    1.18
    Activations Density 0.018%

    No Known Activations