© 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. 5053
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation with specific following characters

    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
    0.32
     enam
    0.26
     karate
    0.26
     and
    0.25
     tenor
    0.25
    <0xBC>
    0.24
     nobles
    0.24
     clothing
    0.23
     propeller
    0.23
    큥
    0.23
    POSITIVE LOGITS
    ע
    0.25
    o
    0.24
    Thats
    0.23
    Acetyl
    0.22
    europe
    0.22
    USP
    0.22
    THON
    0.22
    Weitere
    0.22
    Caso
    0.21
    ্লীল
    0.21
    Activations Density 0.129%

    No Known Activations