© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 11665
    Prev
    Next
    INDEX
    Explanations

    numbers and days

    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
     bore
    0.84
     Slightly
    0.82
     गुणा
    0.82
     slightly
    0.81
     हळ
    0.80
    [:-
    0.79
    緹
    0.78
     desarrollando
    0.77
     divided
    0.76
     različ
    0.76
    POSITIVE LOGITS
     trifling
    0.94
    ർ
    0.93
     insurmountable
    0.92
     paltry
    0.91
     pitiful
    0.91
    街
    0.89
    Remaining
    0.89
    ញ្
    0.88
    ޓ
    0.86
    
    0.83
    Activations Density 0.476%

    No Known Activations