© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 10540
    Prev
    Next
    INDEX
    Explanations

    extra [noun]

    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_17_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
    이
    1.67
    ன்
    1.54
    te
    1.54
    म
    1.54
    i
    1.52
     decently
    1.51
    ك
    1.51
    نه
    1.50
    行き
    1.49
    OPHY
    1.49
    POSITIVE LOGITS
    ordinaire
    2.58
    ordinary
    2.57
    ordin
    2.17
    ctions
    1.90
    followfollow
    1.80
    judicial
    1.79
    ORDIN
    1.77
    escol
    1.72
    তিরিক্ত
    1.68
    preneur
    1.66
    Activations Density 0.078%

    No Known Activations