© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220069
    Prev
    Next
    INDEX
    Explanations

    political instability and uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     बाव
    0.38
     сатып
    0.38
    さに
    0.37
     यहां
    0.37
     समी
    0.36
    ამო
    0.36
     alerta
    0.36
    녀
    0.36
    надцати
    0.36
    ற்
    0.35
    POSITIVE LOGITS
    ==",
    0.38
    Sup
    0.38
    куда
    0.38
     tat
    0.37
     Augustine
    0.37
     yaw
    0.37
     stature
    0.37
    ^+,
    0.37
     coercion
    0.36
     Tat
    0.36
    Activations Density 0.001%

    No Known Activations