© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151244
    Prev
    Next
    INDEX
    Explanations

    political party election scenarios

    np_acts-logits-general · gemini-2.5-flash-lite

    why people think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     ಬಹಳ
    0.46
    利用者
    0.45
     길이
    0.45
    ῥ
    0.45
    גד
    0.44
    atórios
    0.43
    igram
    0.43
    hilangan
    0.43
    창
    0.43
    도
    0.43
    POSITIVE LOGITS
     Yup
    0.51
     Jak
    0.50
     jk
    0.48
     fryer
    0.48
     Determining
    0.47
     Yep
    0.46
     sprawie
    0.46
     使っ
    0.46
     ulteriori
    0.46
     reprinted
    0.45
    Activations Density 0.001%

    No Known Activations