© 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. 4724
    Prev
    Next
    INDEX
    Explanations

    Llama 2

    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
     chiff
    1.57
     marvellous
    1.54
    햅
    1.41
     iht
    1.40
    GBP
    1.40
    Twig
    1.39
    avourable
    1.39
     Sukh
    1.37
    UW
    1.31
    Stabilise
    1.31
    POSITIVE LOGITS
    ἀ
    1.45
    vedo
    1.41
    enzione
    1.41
    achusetts
    1.41
    chez
    1.36
     fato
    1.36
    sylvania
    1.30
    โทษ
    1.30
    abeled
    1.29
    וי
    1.29
    Activations Density 0.059%

    No Known Activations