© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74398
    Prev
    Next
    INDEX
    Explanations

    official statements and investigations

    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_10/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
    colgante
    -1.66
     mentre
    -1.52
     harten
    -1.51
    tgärder
    -1.36
    </h2>
    -1.36
     Werken
    -1.35
     WHILE
    -1.34
     Não
    -1.31
     molti
    -1.30
     blancas
    -1.30
    POSITIVE LOGITS
     and
    2.02
     for
    1.50
     also
    1.43
     \
    1.17
    also
    1.16
     bono
    1.16
     أيضًا
    1.15
     penilaian
    1.13
     always
    1.13
     massif
    1.09
    Activations Density 0.047%

    No Known Activations