© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 7907
    Prev
    Next
    INDEX
    Explanations

    political parties and leaders

    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
    నే
    1.53
    。
    1.45
    ecause
    1.43
    ்ச
    1.31
     труд
    1.30
     emit
    1.27
     estrict
    1.27
    bock
    1.25
     وهذه
    1.23
     чрезвы
    1.22
    POSITIVE LOGITS
    ด์
    1.75
    ून
    1.54
    aj
    1.46
    กำ
    1.44
    ย
    1.42
    TRA
    1.39
    т
    1.38
     Clinton
    1.36
    вим
    1.35
    ści
    1.34
    Activations Density 0.035%

    No Known Activations