© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 3
    Prev
    Next
    INDEX
    Explanations

    blog post Review

    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_16k_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
    ات
    0.78
    ר
    0.77
    ের
    0.76
    те
    0.70
    போன்ற
    0.70
    ों
    0.69
    ی
    0.69
    a
    0.68
    ल
    0.67
    ா
    0.65
    POSITIVE LOGITS
    principal
    0.55
     bild
    0.54
    \{
    0.52
    ie
    0.51
     Owing
    0.51
    <0x80>
    0.51
    IZONTAL
    0.50
    ap
    0.50
    ↵↵
    0.49
    abre
    0.49
    Activations Density 19.521%

    No Known Activations