© 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. 121310
    Prev
    Next
    INDEX
    Explanations

    impeachment trial

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

    building upon foundations

    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
    ┃
    0.48
    多数
    0.46
     workers
    0.46
     phone
    0.46
    부가
    0.46
     sober
    0.45
     bowel
    0.45
    탕
    0.44
     father
    0.44
     king
    0.44
    POSITIVE LOGITS
     függvény
    0.48
     λί
    0.45
     kife
    0.45
    ifle
    0.45
    ilder
    0.45
     นึง
    0.45
    柛
    0.45
    ilte
    0.45
    asal
    0.44
    rosse
    0.44
    Activations Density 0.000%

    No Known Activations