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. 22-GEMMASCOPE-2-RES-16K
    4. 838
    Prev
    Next
    INDEX
    Explanations

    tokyo, help, start

    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_22_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
     δεν
    1.12
    的操作
    1.08
     是否
    1.07
     موجود
    1.07
     to
    1.06
    n
    1.05
     తప్ప
    1.05
    ことを
    1.05
     وش
    1.04
    (/\
    1.03
    POSITIVE LOGITS
    ppled
    2.15
    ppling
    2.11
    asting
    1.95
    ponym
    1.94
    othed
    1.84
    ffee
    1.77
    pless
    1.70
    kyo
    1.65
     whom
    1.61
     be
    1.60
    Activations Density 0.433%

    No Known Activations