© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 4073
    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_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
    1
    1.11
    6
    1.11
    4
    1.00
    8
    0.97
    5
    0.95
    3
    0.89
    7
    0.88
    षी
    0.88
    2
    0.87
    9
    0.84
    POSITIVE LOGITS
    ).
    0.88
    qualiter
    0.86
    uffix
    0.84
     pertinente
    0.79
    の位置
    0.78
    を作
    0.77
     নির্ণ
    0.77
    junctive
    0.77
    യാൾ
    0.76
     должности
    0.76
    Activations Density 0.997%

    No Known Activations