© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8536
    Prev
    Next
    INDEX
    Explanations

    times or twice

    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_31_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
    一旦
    0.74
    ⅜
    0.65
     once
    0.65
     Once
    0.62
    一点
    0.62
     Supplied
    0.59
    一次
    0.58
    ​—
    0.58
     Muitos
    0.57
    ෙන
    0.57
    POSITIVE LOGITS
     ಹೀ
    0.60
     подряд
    0.60
    sal
    0.59
     woord
    0.56
    oos
    0.55
     కంటే
    0.55
    Olympic
    0.54
    zos
    0.53
     erwähnt
    0.53
     sal
    0.52
    Activations Density 0.084%

    No Known Activations