© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11674
    Prev
    Next
    INDEX
    Explanations

    Artificial intelligence and 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_13_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
     features
    0.98
     stuff
    0.85
    ,
    0.84
    features
    0.83
    やお
    0.83
     assoc
    0.81
     prim
    0.80
    stuff
    0.80
     unattended
    0.78
     secondary
    0.77
    POSITIVE LOGITS
     demokrasi
    1.25
     demokrat
    1.19
    公元
    1.14
     caranya
    1.12
    ^{*}=
    1.11
    鴟
    1.10
     Politik
    1.09
     Stelle
    1.09
    Política
    1.08
     осигура
    1.07
    Activations Density 0.000%

    No Known Activations