© 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. 2762
    Prev
    Next
    INDEX
    Explanations

    from smallest to largest

    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
     герои
    0.59
    ikoa
    0.59
    蝠
    0.58
    vs
    0.57
     robo
    0.56
     opposites
    0.55
    versus
    0.54
     vs
    0.54
     monsters
    0.54
     monster
    0.54
    POSITIVE LOGITS
    ga
    0.73
    억
    0.68
    IRT
    0.68
    antemente
    0.68
    सिल
    0.65
    漆
    0.65
    ಮನ
    0.64
     ಭ
    0.64
    endige
    0.62
     Bid
    0.62
    Activations Density 0.231%

    No Known Activations