© 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. 26794
    Prev
    Next
    INDEX
    Explanations

    and a determiners

    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
     forKey
    -1.56
    سيم
    -1.48
     varchar
    -1.48
    corrhi
    -1.48
     môžete
    -1.46
     JpaRepository
    -1.41
     tevreden
    -1.37
     SqlConnection
    -1.37
     vacía
    -1.36
    konos
    -1.34
    POSITIVE LOGITS
     a
    3.75
     an
    2.06
     plenty
    1.91
     lots
    1.40
    an
    1.35
     gosto
    1.34
     herbst
    1.20
     two
    1.19
     jugu
    1.17
    Estr
    1.17
    Activations Density 0.045%

    No Known Activations