© 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. 82909
    Prev
    Next
    INDEX
    Explanations

    said claimed indicates

    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
     with
    -1.41
     we
    -1.36
     you
    -1.30
    我们
    -1.21
     now
    -1.17
     where
    -1.16
     which
    -1.16
     our
    -1.09
     мы
    -1.06
     any
    -1.00
    POSITIVE LOGITS
     someone
    1.38
     quelqu
    1.27
     deux
    1.18
    SOME
    1.15
     algún
    1.13
     sadece
    1.13
    榎
    1.09
    someone
    1.09
    不止
    1.09
    some
    1.08
    Activations Density 0.042%

    No Known Activations