© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4620
    Prev
    Next
    INDEX
    Explanations

    encourage

    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
    物は
    1.49
    入手
    1.47
    lebihan
    1.46
    irá
    1.41
    섰
    1.41
     abertura
    1.40
    iót
    1.36
    ılmış
    1.36
    liel
    1.36
    買い
    1.36
    POSITIVE LOGITS
     Et
    1.37
     Cour
    1.31
     Mayer
    1.24
     Siv
    1.23
     unic
    1.21
     Γ
    1.21
     Jab
    1.16
     poor
    1.16
     Honor
    1.16
    ‏
    1.16
    Activations Density 0.047%

    No Known Activations