© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11791
    Prev
    Next
    INDEX
    Explanations

    low sound descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ondon
    1.57
     (\"
    1.54
     AGRE
    1.49
     $-$
    1.47
     বিন্দু
    1.44
    Fir
    1.44
     गोल
    1.43
     বক্তব্য
    1.43
     (\$
    1.41
    ᵔ
    1.40
    POSITIVE LOGITS
     insomnia
    1.70
     stressful
    1.62
     stressors
    1.57
     tribulations
    1.54
     heartache
    1.53
     PTSD
    1.44
     adversity
    1.42
     loneliness
    1.42
     viciss
    1.41
     stress
    1.40
    Activations Density 0.222%

    No Known Activations