© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5438
    Prev
    Next
    INDEX
    Explanations

    state change or occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
    適切な
    0.75
    O
    0.73
    NoSuch
    0.73
    Implicit
    0.73
    สร้าง
    0.72
    purpose
    0.70
     большое
    0.69
     أبر
    0.68
    妛
    0.68
    rcode
    0.68
    POSITIVE LOGITS
     become
    1.13
     becomes
    0.95
     Become
    0.90
    become
    0.88
     Overall
    0.85
     overall
    0.85
     되어
    0.84
     became
    0.84
     становится
    0.81
     ficando
    0.81
    Activations Density 0.090%

    No Known Activations