© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4094
    Prev
    Next
    INDEX
    Explanations

    JSON format

    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_29_width_65k_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
    朔
    0.88
     Guadalupe
    0.85
     राघव
    0.83
     factor
    0.70
    Factor
    0.69
    otek
    0.67
    ThreadGroup
    0.67
    漪
    0.67
     టిప్పు
    0.67
    sinx
    0.67
    POSITIVE LOGITS
     JSON
    3.32
    JSON
    3.18
    json
    3.00
     json
    2.95
    Json
    2.71
     Json
    2.67
     JSONObject
    2.03
    JSONObject
    2.02
     jsonData
    1.91
    jsonData
    1.89
    Activations Density 1.336%

    No Known Activations