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. 7472
    Prev
    Next
    INDEX
    Explanations

    division or grouping

    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
     strani
    3.32
    istic
    2.72
     kome
    2.70
     yung
    2.69
    तमंद
    2.67
    lös
    2.61
     misalkan
    2.59
    렛
    2.53
     percentuale
    2.53
     deci
    2.53
    POSITIVE LOGITS
    en
    3.10
    regation
    3.10
     nibb
    2.92
    онов
    2.91
    MIB
    2.86
    ल
    2.84
    رض
    2.83
    बाजी
    2.82
    ی
    2.82
    ました
    2.81
    Activations Density 0.040%

    No Known Activations