© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4991
    Prev
    Next
    INDEX
    Explanations

    sense of / space to

    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
     ਜ਼
    0.89
     =$
    0.89
    sigs
    0.83
    ສາ
    0.83
     /$
    0.82
     Seals
    0.82
    ৌ
    0.80
    时的
    0.79
    substrate
    0.78
    το
    0.78
    POSITIVE LOGITS
     "*"
    0.65
     nowhere
    0.63
     якого
    0.63
    ্টি
    0.63
     مرف
    0.62
    которые
    0.62
    ন্থ
    0.62
    fulness
    0.62
     hånd
    0.61
     것처럼
    0.61
    Activations Density 0.049%

    No Known Activations