© 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. 4075
    Prev
    Next
    INDEX
    Explanations

    addressing problems and issues

    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
     demora
    1.39
     Aspergillus
    1.27
     happenings
    1.25
     atent
    1.20
     voluntarios
    1.18
    rophes
    1.17
    =>$
    1.16
    ambh
    1.15
     bú
    1.14
     Involvement
    1.13
    POSITIVE LOGITS
     root
    1.65
    葢
    1.56
    见过
    1.51
    ковь
    1.51
     trunk
    1.51
     wits
    1.50
     admirably
    1.50
     aead
    1.49
     الأساس
    1.48
     основним
    1.47
    Activations Density 0.120%

    No Known Activations