© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14838
    Prev
    Next
    INDEX
    Explanations

    Happy Birthday or Mother's Day greetings

    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_13_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
    pati
    1.29
    ící
    1.24
     lancio
    1.19
    みんな
    1.17
    lovers
    1.16
    ievers
    1.15
    羡
    1.15
    その
    1.14
    いろんな
    1.12
    สำหรับ
    1.10
    POSITIVE LOGITS
     bulk
    1.18
     plastic
    1.16
     cytoplasm
    1.12
     കൊല്ല
    1.11
     disadvantage
    1.10
     possession
    1.10
     post
    1.10
    પણે
    1.08
     mobility
    1.06
     ownership
    1.05
    Activations Density 0.030%

    No Known Activations