© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 148704
    Prev
    Next
    INDEX
    Explanations

    Would you like to hear

    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
     organismos
    0.76
     fiyat
    0.74
    宪
    0.74
     comentar
    0.74
     comments
    0.73
    垷
    0.73
     поведение
    0.73
     koment
    0.72
     davran
    0.72
     cena
    0.72
    POSITIVE LOGITS
    すみ
    0.64
    Third
    0.61
    ્રી
    0.60
    etailed
    0.58
     Third
    0.58
    third
    0.58
    ә
    0.57
     তৃতীয়
    0.57
    record
    0.56
     कपल
    0.56
    Activations Density 0.004%

    No Known Activations