© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 16
    Prev
    Next
    INDEX
    Explanations

    states of being subjected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    нення
    1.58
    보기
    1.56
    низ
    1.51
     Erklärung
    1.49
    пей
    1.49
     étude
    1.48
     зробити
    1.47
    ㍉
    1.46
    istoire
    1.46
     защиту
    1.45
    POSITIVE LOGITS
     seduced
    1.86
     lured
    1.83
     intimidated
    1.82
     overwhelmed
    1.73
     harassed
    1.70
     distracted
    1.70
     tricked
    1.68
     bombarded
    1.65
     fooled
    1.64
     involved
    1.63
    Activations Density 2.675%

    No Known Activations