© 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. 29-GEMMASCOPE-2-RES-262K
    7. 149924
    Prev
    Next
    INDEX
    Explanations

    lightheaded

    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_29_width_262k_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
     povos
    0.76
    ത്മ
    0.76
    Repartition
    0.73
    Produ
    0.70
    owaną
    0.70
    roduction
    0.69
    ıld
    0.68
     삽
    0.68
     প্রজ
    0.68
    Writes
    0.68
    POSITIVE LOGITS
     sty
    0.85
     competencies
    0.69
     dizziness
    0.68
     incompetence
    0.67
     couleurs
    0.65
     may
    0.65
     ईमेल
    0.65
    절
    0.64
     hairstyles
    0.64
     შეგი
    0.64
    Activations Density 0.001%

    No Known Activations