© 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. 3360
    Prev
    Next
    INDEX
    Explanations

    do you want to know

    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
     வினை
    0.67
     creeps
    0.58
     sejak
    0.58
    כים
    0.58
    它
    0.58
     শিল্পের
    0.58
     गुण
    0.58
     brukes
    0.58
     fases
    0.57
     nämlich
    0.57
    POSITIVE LOGITS
    স্ব
    0.69
    ágenes
    0.66
    achd
    0.64
    শার
    0.64
    ү
    0.63
    achtet
    0.63
    覧
    0.62
     Providing
    0.61
    ંત
    0.61
     providing
    0.61
    Activations Density 0.023%

    No Known Activations