© 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. 22-GEMMASCOPE-RES-131K
    7. 38661
    Prev
    Next
    INDEX
    Explanations

    upon entering or arriving

    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_22/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
     sometimes
    -1.17
     during
    -1.16
     often
    -1.14
     quando
    -1.12
     cuando
    -1.12
     for
    -1.11
     Gläub
    -1.05
    tvrt
    -1.03
     end
    -1.03
     use
    -1.02
    POSITIVE LOGITS
     сразу
    1.67
     immediately
    1.65
    まずは
    1.46
    immediately
    1.45
    いきなり
    1.43
    Immediately
    1.38
     greeted
    1.36
     subito
    1.35
     Immediately
    1.30
    まず
    1.29
    Activations Density 0.026%

    No Known Activations