© 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. 1787
    Prev
    Next
    INDEX
    Explanations

    app version

    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
    s
    3.55
    n
    3.08
    ل
    3.00
    ड
    2.95
    ون
    2.95
    ামুটি
    2.76
    ɳ
    2.72
    blow
    2.65
    ات
    2.64
    র
    2.64
    POSITIVE LOGITS
    พลิ
    3.31
    欬
    3.01
     harap
    3.00
     phare
    2.96
     stup
    2.92
    ından
    2.84
     mikä
    2.83
    蓣
    2.79
    凤凰
    2.64
     mga
    2.54
    Activations Density 0.063%

    No Known Activations