© 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. 242217
    Prev
    Next
    INDEX
    Explanations

    Jair Bolsonaro; mistakes; usually

    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
    ɖ
    0.56
    f
    0.53
    ad
    0.48
     Americas
    0.48
    加强
    0.47
    ACM
    0.47
    门的
    0.47
    ۽
    0.46
     Peppers
    0.46
    వంటి
    0.44
    POSITIVE LOGITS
     він
    0.53
     чолові
    0.52
    人も
    0.50
     نار
    0.46
     нрави
    0.45
     पनि
    0.44
     کیا
    0.44
    ತ್ರೆ
    0.44
     vaisseau
    0.43
     perturb
    0.43
    Activations Density 0.000%

    No Known Activations