© 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. 19740
    Prev
    Next
    INDEX
    Explanations

    stark differences, reminder, violation, simplicity

    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
     Then
    -2.27
     It
    -2.22
     Possibly
    -2.17
     Truly
    -2.09
     econó
    -2.08
     Primarily
    -2.05
     fís
    -2.03
     Which
    -2.00
     In
    -1.98
     This
    -1.97
    POSITIVE LOGITS
    Ꮉ
    2.42
     هاي
    2.34
     SECON
    2.31
    ༵
    2.30
     utro
    2.23
     uan
    2.20
     INFIN
    2.20
     mye
    2.17
    ㈯
    2.17
     dvs
    2.16
    Activations Density 0.001%

    No Known Activations