© 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. 2870
    Prev
    Next
    INDEX
    Explanations

    inverse function

    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
    ற்
    0.80
    icação
    0.77
     drücken
    0.75
     treads
    0.75
    quear
    0.72
    ляют
    0.72
     servers
    0.71
    𝓸
    0.68
    দ্বীপ
    0.68
    imary
    0.68
    POSITIVE LOGITS
     bintang
    0.76
     stargazer
    0.75
     Dela
    0.75
     <--
    0.74
     发表于
    0.73
     Ingen
    0.72
    ASC
    0.72
    、“
    0.72
     Dee
    0.71
    msk
    0.70
    Activations Density 0.000%

    No Known Activations