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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15204
    Prev
    Next
    INDEX
    Explanations

    latex, unicode, and code syntax

    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_17_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
    ва
    2.27
    ed
    2.18
    ित
    2.09
    
    1.93
    
    1.92
    υ
    1.92
    ►
    1.89
     prong
    1.86
    ку
    1.85
     pongo
    1.80
    POSITIVE LOGITS
    जिस्ट
    1.70
    و
    1.66
    chnet
    1.60
    સ
    1.50
     نفسه
    1.50
    გუფი
    1.47
    onResume
    1.47
    লে
    1.45
    atk
    1.44
    čkom
    1.39
    Activations Density 0.043%

    No Known Activations