© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3450
    Prev
    Next
    INDEX
    Explanations

    shapes

    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
    s
    1.48
    ounding
    1.37
    a
    1.32
    ه
    1.29
    ات
    1.25
    i
    1.22
    ivalence
    1.21
    added
    1.21
    вания
    1.20
    Prayer
    1.17
    POSITIVE LOGITS
    輙
    1.82
    成像
    1.64
     inhom
    1.61
    čku
    1.61
     sitä
    1.57
     mettere
    1.57
     utilises
    1.57
     osią
    1.56
     raggiungere
    1.55
    stvu
    1.55
    Activations Density 0.001%

    No Known Activations