© 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. 4286
    Prev
    Next
    INDEX
    Explanations

    lists of names and years

    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
    粈
    0.75
     irure
    0.72
    綗
    0.71
    <unused676>
    0.71
    رځ
    0.71
    henius
    0.71
    াদিগের
    0.69
    mene
    0.69
     বলিয়াছেন
    0.68
     सर्किल
    0.68
    POSITIVE LOGITS
     plans
    0.73
     बदला
    0.68
    plans
    0.66
     Turns
    0.66
    eward
    0.65
     want
    0.65
    一半
    0.65
     turns
    0.65
     Rename
    0.65
    耗
    0.62
    Activations Density 0.024%

    No Known Activations