© 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. 18812
    Prev
    Next
    INDEX
    Explanations

    "Our" followed by describing nouns

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

    "our" and subsequent nouns

    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
    在
    0.66
    의
    0.64
    시킨
    0.63
    的
    0.63
     один
    0.61
    았
    0.61
     должен
    0.61
     podía
    0.60
    「
    0.60
    ある
    0.60
    POSITIVE LOGITS
     ourselves
    1.09
     наших
    0.88
     våra
    0.84
    ad
    0.82
    larımız
    0.80
     ہمارے
    0.79
     our
    0.78
     nuestras
    0.78
     ನಮ್ಮ
    0.78
     nuestros
    0.76
    Activations Density 0.240%

    No Known Activations