© 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. 13-GEMMASCOPE-2-RES-16K
    7. 3098
    Prev
    Next
    INDEX
    Explanations

    when immediately

    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_13_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
    fY
    0.78
     மனித
    0.74
     Wipe
    0.73
     уже
    0.72
    Анд
    0.69
     圆
    0.69
    மனித
    0.69
    लिटी
    0.69
     أ
    0.68
     لش
    0.68
    POSITIVE LOGITS
     coup
    0.84
     when
    0.84
     whenever
    0.76
     khi
    0.74
    เมื่อ
    0.72
     opportune
    0.70
     conversion
    0.69
     convert
    0.68
     appropriate
    0.68
     vera
    0.67
    Activations Density 0.225%

    No Known Activations