© 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. 5514
    Prev
    Next
    INDEX
    Explanations

    parallel lines, transport, pumping, beams

    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
    على
    1.48
    onu
    1.48
    汅
    1.44
    ען
    1.41
    מ
    1.41
    렴
    1.40
    vered
    1.37
    enia
    1.34
    니아
    1.34
    ంబేద్కర్
    1.33
    POSITIVE LOGITS
    То
    1.74
    };
    1.67
     headwinds
    1.54
    Та
    1.48
     faites
    1.46
     radiographs
    1.46
    Το
    1.41
    llll
    1.38
    b
    1.37
     auront
    1.35
    Activations Density 0.019%

    No Known Activations