© 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. 4955
    Prev
    Next
    INDEX
    Explanations

    very followed by descriptive words

    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
     would
    0.91
     Daunting
    0.80
    /−
    0.76
    ું
    0.74
    ampi
    0.72
     should
    0.70
     vs
    0.69
     than
    0.69
     challenging
    0.69
     versus
    0.68
    POSITIVE LOGITS
    bona
    0.78
    垷
    0.77
     ವಿರುದ್ಧ
    0.75
     души
    0.74
     定义
    0.74
     act
    0.73
     poca
    0.72
    poque
    0.71
    basics
    0.71
    𝚇
    0.69
    Activations Density 0.143%

    No Known Activations