© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42628
    Prev
    Next
    INDEX
    Explanations

    psychological control and infrastructure

    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
     単
    0.79
     Nucle
    0.72
     destinée
    0.72
    િંગ
    0.71
    ək
    0.71
     personnaliser
    0.71
     första
    0.71
    iphat
    0.71
    વિ
    0.70
    ARIFF
    0.70
    POSITIVE LOGITS
     unexplored
    0.91
    and
    0.85
    美味しい
    0.79
    ร้าย
    0.78
    ม
    0.74
    绎
    0.74
    char
    0.73
    দ
    0.72
    ק
    0.71
    sun
    0.71
    Activations Density 0.000%

    No Known Activations