© 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. 68765
    Prev
    Next
    INDEX
    Explanations

    Eco Bonds

    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
     their
    -1.54
     in
    -1.34
     just
    -1.29
     more
    -1.19
     from
    -1.18
     really
    -1.12
     so
    -1.10
     at
    -1.09
     an
    -1.08
     possibly
    -1.08
    POSITIVE LOGITS
    rée
    1.12
    ully
    1.09
     continúas
    1.07
     nimmer
    1.03
     rr
    1.01
    agerie
    1.01
     изменения
    1.00
     hinzugefügt
    0.99
    ŚCI
    0.98
     ọ
    0.98
    Activations Density 0.004%

    No Known Activations