© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14627
    Prev
    Next
    INDEX
    Explanations

    wikipedia.org urls

    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
    狽
    2.82
    kid
    2.36
    defe
    2.31
     реша
    2.23
     Inv
    2.23
    狈
    2.12
    nang
    2.08
    ayer
    1.94
    true
    1.93
    чаем
    1.93
    POSITIVE LOGITS
    വസ്ഥ
    2.24
     rado
    2.14
     rump
    2.11
    ﻟ
    2.11
    あまり
    2.09
     opérés
    2.08
    χής
    2.08
     brak
    2.06
    ﺓ
    2.04
     Hull
    2.03
    Activations Density 0.011%

    No Known Activations