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-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 444
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     Use
    0.33
    RE
    0.31
     Using
    0.31
    IF
    0.31
     "
    0.31
     using
    0.31
     用
    0.30
     bruke
    0.30
    用
    0.30
     Choose
    0.30
    POSITIVE LOGITS
    র্ঘট
    0.35
     позволяет
    0.34
     предотвра
    0.34
     inconsistencies
    0.34
     позволяют
    0.34
    可知
    0.34
    തീ
    0.32
    ŭ
    0.32
     mencegah
    0.31
    ungkinkan
    0.31
    Activations Density 0.149%

    No Known Activations