© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9677
    Prev
    Next
    INDEX
    Explanations

    access to

    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_17_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
    न
    3.37
    д
    2.50
     zog
    2.40
    د
    2.22
    ು
    2.19
     এছাড়াও
    2.18
    friction
    2.15
    ísticas
    2.13
    ーション
    2.10
    دق
    2.09
    POSITIVE LOGITS
    য়ান
    3.00
    Deine
    2.84
    ется
    2.66
     hatá
    2.37
     publicKey
    2.36
     sunken
    2.33
    OrElse
    2.32
    тиви
    2.30
     remoto
    2.28
    ༅
    2.27
    Activations Density 0.154%

    No Known Activations