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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 309
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Sehingga
    1.40
     понрави
    1.38
    бр
    1.37
    资源的
    1.37
    powied
    1.35
     menambahkan
    1.35
    Ļ
    1.34
     COMEN
    1.33
    Οι
    1.33
    Ϊ
    1.32
    POSITIVE LOGITS
     huddled
    2.05
     sitting
    2.03
     perched
    1.94
     standing
    1.94
     lying
    1.84
     naked
    1.83
     seated
    1.81
     staring
    1.80
     crouching
    1.77
     resting
    1.77
    Activations Density 4.183%

    No Known Activations