© 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. 10685
    Prev
    Next
    INDEX
    Explanations

    complex social and emotional themes

    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
     大型
    2.28
     แนว
    2.23
     Các
    2.15
    ⾼
    2.13
     Ngoài
    2.06
     Кур
    2.05
     主要
    2.04
     毛
    2.02
     ลักษณะ
    1.97
     ניתן
    1.96
    POSITIVE LOGITS
     estrella
    1.61
     drin
    1.60
     envoyer
    1.52
    il
    1.52
     yelling
    1.49
     blah
    1.49
    ut
    1.45
     justo
    1.44
     gak
    1.42
     filho
    1.42
    Activations Density 0.312%

    No Known Activations