© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2491
    Prev
    Next
    INDEX
    Explanations

    multilingual code or structured text

    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_16k_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
                        
    3.62
    ties
    3.50
    ла
    3.43
    𝔱
    3.33
    /−
    3.28
                         
    3.08
    のは
    3.03
    𝙏
    3.01
    2.95
    letzt
    2.95
    POSITIVE LOGITS
    ル
    3.75
    로
    3.63
    లో
    3.51
    गरानी
    3.39
    тен
    3.28
    س
    3.24
    ির
    3.24
    ע
    3.20
    m
    3.14
    ባድ
    3.14
    Activations Density 0.169%

    No Known Activations