© 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. 34-GEMMASCOPE-RES-131K
    7. 82616
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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_34/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
     like
    -1.46
     also
    -1.34
     such
    -1.22
     not
    -1.20
     so
    -1.16
     should
    -1.12
    ;
    -1.06
     sizable
    -1.05
     does
    -1.04
     or
    -1.03
    POSITIVE LOGITS
    ,
    1.23
     día
    1.19
    ،
    1.09
    otras
    1.09
     rembourse
    1.08
    青空
    1.08
     attirer
    1.07
    ruary
    1.06
     assise
    1.06
     يونيو
    1.05
    Activations Density 0.060%

    No Known Activations