© 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. 1450
    Prev
    Next
    INDEX
    Explanations

    rust code with #

    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
    \">\
    1.19
     remont
    1.14
    ẹ
    1.11
    nrows
    1.10
    颀
    1.06
    ')]
    1.05
     toa
    1.04
     Vando
    1.03
    enko
    1.02
    烘
    1.01
    POSITIVE LOGITS
    key
    0.90
    URI
    0.89
    egin
    0.87
    üglich
    0.86
    Cannot
    0.85
     Pie
    0.85
    Icon
    0.85
    COC
    0.84
    орк
    0.84
    渋谷
    0.83
    Activations Density 0.236%

    No Known Activations