© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6398
    Prev
    Next
    INDEX
    Explanations

    Politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     politiche
    0.84
     versiones
    0.79
    Minister
    0.79
    THEOREM
    0.78
    णिज्य
    0.76
    noch
    0.76
    ist
    0.75
    ">{{
    0.73
    令牌
    0.73
     prue
    0.71
    POSITIVE LOGITS
     Correct
    0.89
     party
    0.80
     science
    0.79
    correct
    0.77
    scientists
    0.75
    incorrect
    0.75
     correcta
    0.74
    入院
    0.72
     Science
    0.72
     Party
    0.71
    Activations Density 0.031%

    No Known Activations