Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47370
    Prev
    Next
    INDEX
    Explanations

    engine, addition, button

    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_17_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
    ಲೇ
    1.41
    𝘧
    1.36
     пусть
    1.30
    主义
    1.29
    ferencia
    1.25
     segura
    1.22
    𝒇
    1.20
     avvic
    1.20
    你有
    1.20
     savent
    1.20
    POSITIVE LOGITS
    uary
    1.22
    et
    1.18
    ا
    1.14
    IENCE
    1.08
    ات
    1.02
    ric
    0.98
    resse
    0.97
    enture
    0.94
    uar
    0.94
    etzungen
    0.93
    Activations Density 0.003%

    No Known Activations