© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1187
    Prev
    Next
    INDEX
    Explanations

    quantification and approximation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     relativamente
    1.05
     genellikle
    0.98
     अपेक्षाकृत
    0.97
    醚
    0.94
     relativement
    0.94
     öner
    0.94
     অত্যন্ত
    0.93
     skoro
    0.92
     relatif
    0.92
    যদিও
    0.89
    POSITIVE LOGITS
     halfway
    1.12
     half
    0.96
    同期
    0.86
    ொ
    0.83
     unto
    0.80
     universally
    0.80
     Us
    0.80
     midway
    0.78
    半
    0.77
     lunchtime
    0.76
    Activations Density 0.291%

    No Known Activations