© 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. 12727
    Prev
    Next
    INDEX
    Explanations

    throw error

    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
    3.09
    t
    3.04
    tan
    2.85
    د
    2.78
    tra
    2.49
    tale
    2.45
    tir
    2.43
    tum
    2.39
    ிய
    2.35
    tint
    2.32
    POSITIVE LOGITS
    enumValues
    2.55
    Добрый
    2.38
    あくまで
    2.33
    Какой
    2.31
     MAKEINTRESOURCE
    2.28
    нес
    2.26
    -"+
    2.26
     wesentlich
    2.25
    当代
    2.24
    НЫ
    2.22
    Activations Density 0.034%

    No Known Activations