© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 9880
    Prev
    Next
    INDEX
    Explanations

    "you know" to start a phrase

    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
    piel
    1.03
    𝙝
    0.91
    p
    0.88
    ></
    0.87
    justify
    0.86
    плей
    0.86
    pool
    0.86
    unsqueeze
    0.86
    logfile
    0.84
    RetValue
    0.84
    POSITIVE LOGITS
    閬
    1.23
    iste
    1.10
     meest
    1.09
    ği
    1.05
    ных
    1.05
    一些
    1.05
    ون
    1.04
    цию
    1.03
     کیونکہ
    1.03
    引起的
    1.02
    Activations Density 0.114%

    No Known Activations