© 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. 66063
    Prev
    Next
    INDEX
    Explanations

    brand names and proper nouns

    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
     through
    -1.15
     for
    -1.12
     created
    -1.06
    以及
    -0.97
     as
    -0.96
     out
    -0.96
     take
    -0.94
     finally
    -0.94
    стами
    -0.94
    揷
    -0.94
    POSITIVE LOGITS
     zosta
    1.23
     proveedores
    1.09
     áng
    1.07
     frecuentemente
    1.00
     trám
    0.99
     funcionan
    0.98
     encender
    0.98
     empiezan
    0.98
     atividades
    0.97
     sonriente
    0.97
    Activations Density 0.000%

    No Known Activations