© 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. 22-GEMMASCOPE-RES-131K
    7. 73809
    Prev
    Next
    INDEX
    Explanations

    temporal indicators and specific entities

    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
     in
    -1.01
     using
    -0.98
     with
    -0.95
    :
    -0.93
     for
    -0.93
     as
    -0.91
    there
    -0.90
     on
    -0.88
     at
    -0.88
     unusually
    -0.86
    POSITIVE LOGITS
     dépens
    1.10
     disparu
    1.10
     DURING
    1.06
     ponú
    1.05
     trám
    1.05
     affich
    1.05
    ricultural
    1.05
     břez
    1.03
    ICAGO
    1.02
     фир
    1.02
    Activations Density 0.123%

    No Known Activations