© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4952
    Prev
    Next
    INDEX
    Explanations

    lychee, Lyra, citrus, hash tables, order, RAINN

    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_22_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
     दायरे
    0.63
    க்களை
    0.62
     ελλην
    0.62
    elda
    0.59
    訢
    0.59
    设定
    0.59
     шкі
    0.58
    VB
    0.58
    ೂರ್ಯ
    0.57
     solito
    0.56
    POSITIVE LOGITS
    iam
    0.81
    ያው
    0.78
     gült
    0.72
    井
    0.64
     children
    0.63
    ই
    0.62
    یم
    0.62
    א
    0.62
    ровании
    0.62
    ैव
    0.61
    Activations Density 0.116%

    No Known Activations