© 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. 231998
    Prev
    Next
    INDEX
    Explanations

    Trump political machine

    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
    בק
    0.51
     Química
    0.49
    ﭜ
    0.48
    لف
    0.46
    뚤
    0.46
    є
    0.46
    ూ
    0.46
    ੁੱ
    0.45
    тріш
    0.45
    ్రీ
    0.44
    POSITIVE LOGITS
    rova
    0.45
     ይህም
    0.44
    kan
    0.42
    roa
    0.42
    cza
    0.41
    灯
    0.41
    hed
    0.40
    lero
    0.40
    uto
    0.40
     สอน
    0.40
    Activations Density 0.001%

    No Known Activations