© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8730
    Prev
    Next
    INDEX
    Explanations

    Russian political history

    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_31_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
     يمكنك
    0.80
     бизне
    0.79
    Brexit
    0.77
     бизнеса
    0.75
     biznes
    0.75
    🟡
    0.74
    EU
    0.73
     ₽
    0.73
     estándar
    0.72
     стаби
    0.71
    POSITIVE LOGITS
     committees
    0.64
     XII
    0.64
     XI
    0.63
     XIV
    0.63
     convening
    0.61
     revolutionary
    0.58
     XVII
    0.57
     workday
    0.57
     easel
    0.56
     Committee
    0.56
    Activations Density 0.059%

    No Known Activations