© 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. 9536
    Prev
    Next
    INDEX
    Explanations

    1 followed by 9

    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
    ம்
    1.59
    t
    1.57
    o
    1.53
    ه
    1.39
    ு
    1.33
    ে
    1.32
    ture
    1.29
     EdgeInsets
    1.28
    
    1.27
    ым
    1.26
    POSITIVE LOGITS
     isset
    0.99
    henyl
    0.98
    榈
    0.92
    জনাব
    0.91
     lobe
    0.87
     пур
    0.87
    }$}
    0.86
     gotta
    0.85
     colic
    0.85
    /[\
    0.83
    Activations Density 0.010%

    No Known Activations