© 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. 189842
    Prev
    Next
    INDEX
    Explanations

    Pope Francis's statements and origins

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

    Pope, Argentina, speech, Vatican

    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
    歙
    0.44
     itemCount
    0.43
    rection
    0.42
    candles
    0.42
    daction
    0.41
    aison
    0.40
    acts
    0.40
    allele
    0.40
    邃
    0.40
    readyState
    0.40
    POSITIVE LOGITS
     Patagonia
    0.59
     Buenos
    0.58
     Urugu
    0.57
     Boliv
    0.54
     Miguel
    0.54
     Argentina
    0.53
     Uruguay
    0.52
     argentina
    0.52
     Ramirez
    0.51
     Javascript
    0.50
    Activations Density 0.022%

    No Known Activations