© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25528
    Prev
    Next
    INDEX
    Explanations

    conjunctions connecting items

    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
     ᾿
    -1.26
     ridiculously
    -1.23
     Dinas
    -1.22
    すっ
    -1.20
     puramente
    -1.18
    えっ
    -1.18
     delightfully
    -1.17
     exceedingly
    -1.16
     realmente
    -1.14
     rapidamente
    -1.14
    POSITIVE LOGITS
     other
    1.61
     during
    1.45
     throughout
    1.29
     if
    1.16
     as
    1.16
     these
    1.14
     some
    1.13
     several
    1.11
     when
    1.11
     all
    1.11
    Activations Density 0.059%

    No Known Activations