© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40385
    Prev
    Next
    INDEX
    Explanations

    words related topolitics, terror,and journalism

    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
    Negative Logits
     🥰
    0.85
     proficient
    0.82
     💕
    0.81
     thorough
    0.81
     rigorous
    0.81
     very
    0.80
     temperament
    0.80
     style
    0.79
    ☺️
    0.79
     philosophy
    0.79
    POSITIVE LOGITS
     políticos
    0.83
     терро
    0.79
    janja
    0.77
     आतंक
    0.74
     periodistas
    0.73
    ان
    0.73
     ataques
    0.73
     decenas
    0.73
    z
    0.73
    un
    0.72
    Activations Density 0.019%

    No Known Activations