© 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. 34-GEMMASCOPE-RES-131K
    7. 108807
    Prev
    Next
    INDEX
    Explanations

    adjective followed by noun

    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_34/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
     “…
    -1.38
     Jika
    -1.37
     erneut
    -1.34
    Jika
    -1.34
     صلى
    -1.25
    Какво
    -1.25
     dapat
    -1.23
     lecz
    -1.23
     FUCK
    -1.21
     télécommande
    -1.21
    POSITIVE LOGITS
     somebody
    2.31
     things
    2.30
     [
    2.27
     kind
    2.27
     maybe
    2.06
     stuff
    2.02
     everybody
    2.02
     thing
    1.95
     really
    1.90
     probably
    1.88
    Activations Density 0.029%

    No Known Activations