© 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. 22-GEMMASCOPE-RES-131K
    7. 26867
    Prev
    Next
    INDEX
    Explanations

    numbers and days

    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
     pantalon
    -1.41
     tarta
    -1.19
     motocicleta
    -1.19
     alternatif
    -1.18
    artikel
    -1.13
     nimmer
    -1.11
    gangss
    -1.10
    "../
    -1.10
     plafon
    -1.09
     instituições
    -1.09
    POSITIVE LOGITS
     to
    1.38
     m
    1.16
     z
    1.12
     u
    1.11
     l
    1.05
     new
    1.05
     will
    1.03
     b
    1.02
     by
    1.02
     et
    1.01
    Activations Density 0.000%

    No Known Activations