© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11738
    Prev
    Next
    INDEX
    Explanations

    political polarization, specific formulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <(
    1.47
    చారం
    1.42
    몹
    1.39
     diverted
    1.30
    ია
    1.29
    failed
    1.28
    თ
    1.28
     intercepted
    1.27
    <unused1700>
    1.25
     smuggled
    1.25
    POSITIVE LOGITS
     Nach
    1.15
    After
    1.07
     best
    1.03
    的最佳
    1.00
     பிறகு
    0.99
     نوع
    0.98
    Eyes
    0.97
     decisión
    0.97
     här
    0.97
     decisão
    0.96
    Activations Density 0.000%

    No Known Activations