© 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. 4774
    Prev
    Next
    INDEX
    Explanations

    being paramount / critical / important

    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
    徑
    1.35
    ς
    1.30
    alloway
    1.29
    ško
    1.27
    itih
    1.27
    ihilation
    1.26
    στό
    1.26
    sı
    1.25
    sini
    1.25
    ử
    1.24
    POSITIVE LOGITS
     guarant
    1.48
     guaranteed
    1.43
     ideal
    1.39
     perfect
    1.38
     composer
    1.38
     Guaranteed
    1.35
     guarantee
    1.32
     guarantees
    1.32
     prime
    1.31
     Maxime
    1.25
    Activations Density 0.107%

    No Known Activations