© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2160
    Prev
    Next
    INDEX
    Explanations

    civil aircraft

    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
     cust
    0.59
     Inns
    0.56
    ushroom
    0.56
    单纯
    0.54
    avos
    0.53
    钻
    0.53
    渟
    0.53
    出来ます
    0.52
    olia
    0.52
    Ĥ
    0.51
    POSITIVE LOGITS
     Rang
    1.50
    cessor
    1.43
     unsett
    1.41
    Rang
    1.39
    nginx
    1.39
     Bye
    1.39
     enum
    1.37
     Alexei
    1.36
     случи
    1.35
    tailwindcss
    1.35
    Activations Density 0.263%

    No Known Activations