© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9927
    Prev
    Next
    INDEX
    Explanations

    simple, area, types

    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_13_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
    阆
    1.15
    馔
    1.07
    тво
    1.05
    閬
    1.01
     almu
    0.99
    ↷
    0.99
    initWith
    0.97
    蓥
    0.97
    薷
    0.97
     ड्राइ
    0.96
    POSITIVE LOGITS
     Area
    0.96
     Characters
    0.86
    area
    0.82
     Chemical
    0.80
     Pest
    0.78
     area
    0.76
     Type
    0.75
     Jenis
    0.74
     Orte
    0.74
     Areas
    0.73
    Activations Density 0.000%

    No Known Activations