© 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. 3703
    Prev
    Next
    INDEX
    Explanations

    best, most, top ranked

    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
    当前
    1.60
    órios
    1.51
     biedt
    1.50
    اتف
    1.45
    एगा
    1.44
     weltweit
    1.44
    ตอนนี้
    1.40
    ☜
    1.40
     wordt
    1.40
    目前
    1.39
    POSITIVE LOGITS
     なかっ
    2.30
     WAS
    2.06
     ра
    2.03
     وكانت
    2.02
     vardı
    1.99
     fosse
    1.98
     وكان
    1.96
    MeOH
    1.96
     있었
    1.95
     hadde
    1.94
    Activations Density 2.604%

    No Known Activations