© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2319
    Prev
    Next
    INDEX
    Explanations

    show Password, Advance Parole, access token

    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_13_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
     unpublished
    1.58
    nofollow
    1.54
     [];
    1.52
     spl
    1.51
     Franco
    1.49
    関
    1.48
     oxidase
    1.48
    angar
    1.44
    eworthy
    1.43
    Concern
    1.43
    POSITIVE LOGITS
    bill
    1.45
    ਿਕ
    1.38
     hoá
    1.36
    лік
    1.35
     hóa
    1.35
    화를
    1.35
    化的
    1.34
     rek
    1.29
    ್ರಾ
    1.27
    ỷ
    1.26
    Activations Density 0.826%

    No Known Activations