© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3855
    Prev
    Next
    INDEX
    Explanations

    absolute or relative paths and dates

    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
    been
    0.79
    aim
    0.79
    ByName
    0.77
     Ai
    0.73
     Loves
    0.72
     latar
    0.72
     Serm
    0.68
     ૧
    0.68
    Ai
    0.68
    evo
    0.67
    POSITIVE LOGITS
     absolute
    0.79
     absolut
    0.73
    相对于
    0.71
     relative
    0.67
     absol
    0.66
     Absolute
    0.66
    Relative
    0.65
    絕對
    0.64
     относи
    0.64
    绝对
    0.63
    Activations Density 0.233%

    No Known Activations