© 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. 9225
    Prev
    Next
    INDEX
    Explanations

    need to

    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
    班牙
    1.73
    ди
    1.68
     dint
    1.68
    >
    1.66
    zelf
    1.62
    ına
    1.60
    ㈤
    1.58
    蝠
    1.57
     sendo
    1.55
     serem
    1.52
    POSITIVE LOGITS
    臾
    2.17
    ל
    2.00
    ла
    1.98
    رت
    1.77
    ра
    1.67
    तमंद
    1.67
     Passe
    1.66
    lust
    1.59
    不需要
    1.59
    tól
    1.59
    Activations Density 0.380%

    No Known Activations