© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2452
    Prev
    Next
    INDEX
    Explanations

    introducing a specific concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     Revisited
    0.98
     shoved
    0.97
     pushed
    0.96
     encouraged
    0.93
     갔
    0.92
     ALWAYS
    0.91
     Moved
    0.90
     sucked
    0.90
     chased
    0.89
     Speaks
    0.89
    POSITIVE LOGITS
    characteristics
    1.12
    municipal
    1.11
    international
    1.11
    interaction
    1.10
    university
    1.09
    «
    1.09
    public
    1.09
    conclusion
    1.08
    agricultural
    1.07
    introduction
    1.07
    Activations Density 0.205%

    No Known Activations