© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1940
    Prev
    Next
    INDEX
    Explanations

    down your spine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whistle
    1.30
     sûr
    1.28
     humides
    1.27
    
    1.25
    或其他
    1.25
     électriques
    1.23
    //{
    1.23
     як
    1.22
     dalších
    1.20
     อื่น
    1.20
    POSITIVE LOGITS
     this
    1.85
    this
    1.64
    この
    1.59
    Cette
    1.56
     این
    1.45
     उस
    1.44
     your
    1.42
     Auch
    1.42
     the
    1.39
     it
    1.38
    Activations Density 0.799%

    No Known Activations