© 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. 45549
    Prev
    Next
    INDEX
    Explanations

    switches and sockets

    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
    en
    0.89
    Innov
    0.88
    labeled
    0.85
    CAG
    0.85
    tetra
    0.85
    iate
    0.83
    Labeled
    0.82
    ت
    0.82
    Mot
    0.82
    Mic
    0.81
    POSITIVE LOGITS
     όχι
    0.95
    vý
    0.91
     beginnen
    0.89
     keď
    0.88
     dạy
    0.86
     σύμφωνα
    0.86
     όπως
    0.82
     delightfully
    0.82
     ничего
    0.81
     fossils
    0.81
    Activations Density 0.000%

    No Known Activations