© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6786
    Prev
    Next
    INDEX
    Explanations

    ternary, pornography, VPN blocking, burn off, RNNs, tarnished, technica

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    deki
    3.22
    gruppe
    3.11
    tt
    3.06
    da
    2.98
    ം
    2.86
    den
    2.84
    า
    2.75
    do
    2.73
    dır
    2.73
    gruppen
    2.72
    POSITIVE LOGITS
    깐
    2.58
    स्पति
    2.45
    ات
    2.44
    न
    2.39
    на
    2.31
    кой
    2.28
    ের
    2.25
    speople
    2.14
    ва
    2.11
    のが
    2.11
    Activations Density 0.362%

    No Known Activations