© 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. 71846
    Prev
    Next
    INDEX
    Explanations

    after afterward later

    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
    ：
    -1.27
    formerly
    -1.20
     or
    -1.16
     you
    -1.13
    已经
    -1.10
     teknis
    -1.10
     سينما
    -1.09
    hopped
    -1.09
    ;;)
    -1.08
    ⌫
    -1.08
    POSITIVE LOGITS
     later
    1.98
     was
    1.59
     eventually
    1.51
     später
    1.40
    後に
    1.35
     heutigen
    1.32
     späteren
    1.25
     were
    1.19
     afterward
    1.19
    之时
    1.18
    Activations Density 0.089%

    No Known Activations