© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 12016
    Prev
    Next
    INDEX
    Explanations

    comparison and connection

    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
     सबूत
    0.77
     upholding
    0.75
     jealousy
    0.74
    탬
    0.73
     przyczyn
    0.72
    passwd
    0.71
    गौरतलब
    0.70
    容器
    0.70
    خاذ
    0.68
     குழந்தைகள்
    0.66
    POSITIVE LOGITS
    与其他
    1.44
    กับ
    1.33
    与
    1.27
     与
    1.22
    與
    1.17
    ກັບ
    1.06
     किससे
    1.04
    対
    1.02
     against
    1.02
     partner
    1.01
    Activations Density 0.232%

    No Known Activations