© 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-262K
    4. 7149
    Prev
    Next
    INDEX
    Explanations

    placeholder for future analyses

    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
    д
    0.79
     blot
    0.77
     add
    0.70
    add
    0.68
    ors
    0.66
     global
    0.66
     frown
    0.66
    ↵
    0.65
     tolerance
    0.65
    .
    0.65
    POSITIVE LOGITS
     historische
    1.05
    glichkeiten
    0.92
    lcc
    0.90
     äußerst
    0.88
    ⃖
    0.88
    ducting
    0.87
     esclusivamente
    0.87
    el
    0.86
     jüng
    0.86
     vrijdag
    0.85
    Activations Density 0.099%

    No Known Activations