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. 7270
    Prev
    Next
    INDEX
    Explanations

    GPT and other AI models

    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
     chance
    2.62
     llegar
    2.50
    ことがあります
    2.43
     сове
    2.38
    "",
    2.37
     intención
    2.34
    \{\
    2.33
     barometer
    2.30
    こう
    2.28
     fray
    2.28
    POSITIVE LOGITS
    ना
    3.77
    त
    2.97
    ال
    2.42
    ق
    2.41
    اً
    2.39
    en
    2.30
    avantage
    2.27
    liest
    2.24
    uring
    2.23
    美元
    2.23
    Activations Density 0.134%

    No Known Activations