© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1117
    Prev
    Next
    INDEX
    Explanations

    website addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     memak
    0.69
    anned
    0.69
     antib
    0.65
    قافة
    0.62
    呿
    0.62
    ремен
    0.62
    etable
    0.62
    料
    0.62
    敌人
    0.62
    لال
    0.61
    POSITIVE LOGITS
     com
    4.01
    com
    3.74
    COM
    2.79
    org
    2.77
     org
    2.67
    Com
    2.62
     Com
    2.59
     COM
    2.36
    Org
    2.11
    ORG
    2.10
    Activations Density 0.569%

    No Known Activations