© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 12058
    Prev
    Next
    INDEX
    Explanations

    United Nations and member states

    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_16k_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
    ak
    2.06
    らった
    1.73
    тировать
    1.59
    ah
    1.58
    ма
    1.57
    es
    1.53
    轍
    1.52
    씀
    1.45
    ную
    1.43
    ❞
    1.43
    POSITIVE LOGITS
    А
    1.76
    ר
    1.72
     demie
    1.68
    न
    1.66
    ING
    1.63
     Η
    1.61
    Ти
    1.60
    蒉
    1.55
    ले
    1.53
    ❖
    1.53
    Activations Density 0.014%

    No Known Activations