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. 29-GEMMASCOPE-2-RES-262K
    4. 925
    Prev
    Next
    INDEX
    Explanations

    git checkout

    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_29_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
    e
    0.82
    een
    0.78
    side
    0.77
    tail
    0.77
    dem
    0.77
    tire
    0.75
    rear
    0.75
    public
    0.73
    der
    0.73
    then
    0.73
    POSITIVE LOGITS
     FIGURE
    0.97
     INTRODUCTION
    0.88
     CHAPTER
    0.86
     Здравствуйте
    0.85
     δ
    0.81
     ६
    0.80
     Figure
    0.80
     peningkatan
    0.79
     fi
    0.78
     Characteristics
    0.78
    Activations Density 0.000%

    No Known Activations