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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9026
    Prev
    Next
    INDEX
    Explanations

    into equation

    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
     Cumhur
    1.46
     //=>
    1.42
     gimana
    1.31
     bunların
    1.30
     Góc
    1.29
     Şu
    1.29
     Sunak
    1.28
     şu
    1.27
     Osmanlı
    1.27
     Ekonomi
    1.27
    POSITIVE LOGITS
    complete
    0.95
    amm
    0.95
    മ
    0.93
    хи
    0.90
    ми
    0.89
    а
    0.89
    amel
    0.88
    into
    0.87
    aes
    0.86
    ovani
    0.82
    Activations Density 0.002%

    No Known Activations