© 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-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69451
    Prev
    Next
    INDEX
    Explanations

    reading materials and content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bridesmaids
    2.07
    징
    2.02
     investors
    2.01
    führt
    1.98
     appId
    1.97
     appliances
    1.96
     recruiters
    1.94
    헹
    1.94
    cesa
    1.92
     decommissioning
    1.92
    POSITIVE LOGITS
     essays
    1.11
     MAGAZINE
    1.07
     livros
    1.06
     libri
    1.04
     booklet
    0.97
    ertation
    0.96
     Texte
    0.96
     littérature
    0.95
     contenu
    0.95
    的文章
    0.89
    Activations Density 0.015%

    No Known Activations