© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8871
    Prev
    Next
    INDEX
    Explanations

    acronyms and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     將
    1.59
     Одна
    1.59
    𝑦
    1.53
     dingen
    1.48
     Может
    1.45
    將
    1.45
     giornata
    1.43
     pouvoir
    1.42
    𝘁
    1.37
     digraph
    1.37
    POSITIVE LOGITS
    Đi
    1.26
    م
    1.23
     gros
    1.16
    mild
    1.14
    Ricky
    1.10
    Vall
    1.10
    ging
    1.10
    Strawberry
    1.07
    Homemade
    1.07
    Japanese
    1.06
    Activations Density 0.191%

    No Known Activations