© 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. 3993
    Prev
    Next
    INDEX
    Explanations

    how it works

    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
    sberg
    1.55
    usine
    1.36
    }+...
    1.34
    zewski
    1.29
    劉
    1.29
    ますが
    1.23
     zis
    1.22
     $)
    1.21
     sistem
    1.21
     конфи
    1.19
    POSITIVE LOGITS
     transcends
    1.26
    ById
    1.26
     connot
    1.19
    каче
    1.15
    трен
    1.14
     subtypes
    1.13
     torsional
    1.13
    urb
    1.10
    Cron
    1.09
    chte
    1.09
    Activations Density 0.041%

    No Known Activations