© 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. 128976
    Prev
    Next
    INDEX
    Explanations

    compact, slim, affordable format

    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
     when
    -1.33
     although
    -1.24
     despite
    -1.19
     those
    -1.14
     during
    -1.13
     begin
    -1.09
     several
    -1.08
     some
    -1.06
     while
    -1.03
     additional
    -1.03
    POSITIVE LOGITS
     varier
    1.17
     astu
    1.14
     zei
    1.13
     kalender
    1.11
     alarme
    1.09
    ohne
    1.09
     actualité
    1.09
     manier
    1.08
     nœ
    1.05
     mondi
    1.04
    Activations Density 0.075%

    No Known Activations