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. 31-GEMMASCOPE-2-RES-262K
    4. 142
    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_31_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
    jati
    0.59
     juvenil
    0.55
     palk
    0.55
    нным
    0.54
    )]);
    0.54
     mij
    0.54
    sparsebundle
    0.53
    ))],
    0.52
     wonder
    0.52
    RAchievement
    0.51
    POSITIVE LOGITS
     {\
    0.69
    {\
    0.63
     ${\
    0.63
    Department
    0.58
    getDouble
    0.58
    ${\
    0.56
     โรง
    0.56
    flush
    0.55
     {{\
    0.55
    考试
    0.54
    Activations Density 0.000%

    No Known Activations