© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14014
    Prev
    Next
    INDEX
    Explanations

    bubbles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     Lok
    0.53
     Varan
    0.51
     অক্ষম
    0.51
     Observer
    0.49
    雄
    0.48
     Kodak
    0.48
    🚶
    0.48
     Bermuda
    0.48
     firing
    0.47
    Примечания
    0.47
    POSITIVE LOGITS
    Marg
    0.62
    bubble
    0.60
    边
    0.60
    gence
    0.60
     Marcel
    0.60
    வில்
    0.58
     vVertex
    0.57
     نظم
    0.56
     precipit
    0.56
    禇
    0.56
    Activations Density 0.000%

    No Known Activations