© 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. 11937
    Prev
    Next
    INDEX
    Explanations

    intermediate availability instance adopted use

    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
    emon
    0.94
     actionMode
    0.93
    allocate
    0.92
    ழ
    0.91
    село
    0.90
    ং
    0.84
     trail
    0.83
    eland
    0.83
    躬
    0.81
    зайн
    0.80
    POSITIVE LOGITS
     Muitos
    1.35
     Ainda
    1.26
     Due
    1.26
     Debido
    1.24
     Muchos
    1.24
     Um
    1.23
     क्रिस्ट
    1.21
     Algunos
    1.21
    distant
    1.20
     Así
    1.20
    Activations Density 0.000%

    No Known Activations