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. 9-GEMMASCOPE-2-RES-262K
    4. 7659
    Prev
    Next
    INDEX
    Explanations

    generative AI

    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_9_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
    एफ
    2.65
    and
    2.64
    یت
    2.52
    ها
    2.47
    ORY
    2.40
    tedir
    2.37
    🆈
    2.33
    
    2.32
     doubtless
    2.32
    are
    2.27
    POSITIVE LOGITS
    ي
    3.31
    i
    3.24
    ių
    2.72
    𝑎
    2.71
    ли
    2.62
    ات
    2.51
    י
    2.51
    sst
    2.43
    o
    2.42
    a
    2.42
    Activations Density 0.043%

    No Known Activations