© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5195
    Prev
    Next
    INDEX
    Explanations

    writing essays and homework

    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_12_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
    络
    1.65
    咛
    1.59
     lihat
    1.54
    німа
    1.53
    ضرب
    1.52
    жаю
    1.49
    ologa
    1.48
    秘密
    1.47
     Packed
    1.47
    omaly
    1.46
    POSITIVE LOGITS
    writ
    2.17
    contest
    1.93
    stol
    1.86
    assignments
    1.86
    school
    1.82
    holtz
    1.81
    醉
    1.79
    gown
    1.79
    坊
    1.77
    motivated
    1.72
    Activations Density 0.038%

    No Known Activations