© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77024
    Prev
    Next
    INDEX
    Explanations

    in and out transitions

    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
     in
    -1.05
     In
    -1.05
    in
    -0.88
     IN
    -0.88
    IN
    -0.84
    In
    -0.81
    ovala
    -0.81
    协会
    -0.79
    攔
    -0.75
    的呢
    -0.74
    POSITIVE LOGITS
     and
    2.81
    และ
    1.54
     out
    1.29
     și
    1.20
     и
    1.19
     \&
    1.16
     וח
    1.16
     và
    1.11
    out
    1.03
     και
    1.02
    Activations Density 0.034%

    No Known Activations