© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37543
    Prev
    Next
    INDEX
    Explanations

    wide range, hour course, Head North, access key

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ת
    0.92
    م
    0.91
    ất
    0.87
    很多
    0.84
    (["
    0.83
    imgur
    0.82
     graduated
    0.82
     rearr
    0.80
     received
    0.80
    ((\
    0.79
    POSITIVE LOGITS
     larynx
    0.94
    quinoxaline
    0.86
    埼
    0.86
     factorial
    0.80
     бк
    0.79
    quinoxalin
    0.78
     Antes
    0.77
     ఛ
    0.76
     sial
    0.76
     लीजिएगा
    0.76
    Activations Density 0.000%

    No Known Activations