© 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. 45119
    Prev
    Next
    INDEX
    Explanations

    Macedonia; Macedonian

    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
    ে
    1.59
    AU
    1.47
    AN
    1.42
    AK
    1.41
    k
    1.38
    will
    1.36
    the
    1.34
    US
    1.34
    ES
    1.31
    OD
    1.30
    POSITIVE LOGITS
    ت
    1.52
    šnji
    1.49
    nimi
    1.48
    лоти
    1.47
    ziej
    1.46
    ុល
    1.41
    nél
    1.39
    ین
    1.38
    oramic
    1.38
     unidos
    1.38
    Activations Density 0.001%

    No Known Activations