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. 7198
    Prev
    Next
    INDEX
    Explanations

    type of

    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
    問題
    2.05
    ທ່ານ
    2.02
     में
    1.89
    问题
    1.86
    ї
    1.86
     के
    1.85
    the
    1.79
     بأ
    1.76
    מ
    1.76
    У
    1.76
    POSITIVE LOGITS
     course
    1.84
    م
    1.77
    quela
    1.76
    iary
    1.71
     sorts
    1.63
     siebie
    1.60
    is
    1.58
    fi
    1.56
    ാ
    1.55
    ل
    1.52
    Activations Density 1.266%

    No Known Activations