© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1818
    Prev
    Next
    INDEX
    Explanations

    essential or crucial for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    mit
    2.28
    s
    2.17
    sman
    1.98
    دان
    1.97
    pipe
    1.96
    GING
    1.95
    imat
    1.95
    ইংরেজি
    1.89
    ை
    1.88
    sky
    1.86
    POSITIVE LOGITS
     समक्ष
    2.95
    偣
    2.80
    iality
    2.66
     attire
    2.59
     toc
    2.57
     Yelp
    2.56
     backgroundImg
    2.53
    यॉर्क
    2.49
    锷
    2.48
    证券投资基金业协会
    2.47
    Activations Density 0.268%

    No Known Activations