© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2519
    Prev
    Next
    INDEX
    Explanations

    `grep` command and games

    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
     train
    0.93
    xpress
    0.93
    اتها
    0.91
     vist
    0.88
    s
    0.85
    otta
    0.84
    ist
    0.83
    dır
    0.82
     Train
    0.82
    תה
    0.81
    POSITIVE LOGITS
     মুশ
    1.40
    ுகளை
    1.29
     пой
    1.27
     maxx
    1.26
     unsurprisingly
    1.20
     chewy
    1.19
     tallied
    1.18
    が一
    1.18
     captivated
    1.18
    婇
    1.18
    Activations Density 0.004%

    No Known Activations