© 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. 26809
    Prev
    Next
    INDEX
    Explanations

    considerate employer

    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
    </i>
    -1.35
     nimmer
    -1.23
    caneca
    -1.22
    cabeza
    -1.22
     portavoz
    -1.20
    訁
    -1.18
     héroe
    -1.13
    肯定是
    -1.13
    asikan
    -1.13
    Kommentar
    -1.13
    POSITIVE LOGITS
     where
    1.12
    menuhi
    1.11
     it
    1.08
    آب
    1.02
     jaro
    1.00
     and
    0.99
     while
    0.97
     !=
    0.95
     like
    0.94
     hvilke
    0.94
    Activations Density 0.263%

    No Known Activations