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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7401
    Prev
    Next
    INDEX
    Explanations

    "LoRA LSTM"

    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
    o
    1.27
    얼
    1.26
    Д
    1.23
     اینکه
    1.23
    ciamo
    1.20
    */
    1.19
     сообщает
    1.19
    itionally
    1.18
    Enabled
    1.17
    ضل
    1.17
    POSITIVE LOGITS
    𝑬
    1.59
    t
    1.54
    সংখ্য
    1.46
    ت
    1.42
    𝙩
    1.38
     ľudí
    1.38
     ਇਕ
    1.37
    تهم
    1.37
     scoprire
    1.36
    𝒔
    1.36
    Activations Density 0.097%

    No Known Activations