© 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. 34-GEMMASCOPE-RES-131K
    7. 30926
    Prev
    Next
    INDEX
    Explanations

    has been

    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
     still
    -2.03
     first
    -1.45
     currently
    -1.39
     when
    -1.27
     new
    -1.20
    当時は
    -1.18
     soon
    -1.18
     current
    -1.17
     начина
    -1.16
     became
    -1.14
    POSITIVE LOGITS
     since
    3.39
     lately
    2.88
    since
    2.66
     منذ
    2.38
     depuis
    2.36
     SINCE
    2.25
     sejak
    2.13
     Lately
    2.02
     been
    1.94
    Since
    1.94
    Activations Density 0.124%

    No Known Activations