© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10667
    Prev
    Next
    INDEX
    Explanations

    St. Peter's Basilica, Doctor Strange

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    𝑢
    3.09
    愎
    3.05
    𝑚
    2.79
     INST
    2.72
     неко
    2.70
    𝑟
    2.64
     bred
    2.63
    ɮ
    2.63
    ᓂ
    2.61
    Genus
    2.60
    POSITIVE LOGITS
    ை
    2.99
    ील
    2.85
     retirer
    2.64
    スプレイ
    2.63
    ी
    2.62
    ा
    2.59
    मधून
    2.57
    ঠা
    2.51
    ün
    2.47
    ährung
    2.40
    Activations Density 0.012%

    No Known Activations