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. 3660
    Prev
    Next
    INDEX
    Explanations

    livestock and wild animals

    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
     Blüten
    0.81
     Гар
    0.79
     botan
    0.78
    濱
    0.77
     Lé
    0.77
     tsunami
    0.73
     florist
    0.73
     Blume
    0.72
    傘
    0.72
     হাব
    0.72
    POSITIVE LOGITS
     cattle
    2.32
     livestock
    2.22
     cows
    2.19
     sheep
    2.10
    Sheep
    2.08
    cattle
    2.00
    sheep
    1.96
     Livestock
    1.90
     Sheep
    1.90
     herds
    1.89
    Activations Density 0.375%

    No Known Activations