Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38328
    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_12_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
     Kild
    0.92
    วง
    0.89
     ndi
    0.82
    すと
    0.81
     direitos
    0.80
     csoport
    0.80
    λα
    0.79
    ൻ
    0.79
     bilangan
    0.79
     discontent
    0.76
    POSITIVE LOGITS
    theless
    0.78
    poison
    0.76
    POSITORY
    0.74
     Specifically
    0.72
    al
    0.72
     हाउ
    0.71
    once
    0.71
    unlike
    0.70
    /**
    0.69
    destroy
    0.69
    Activations Density 0.000%

    No Known Activations