© 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. 12008
    Prev
    Next
    INDEX
    Explanations

    Gravitational waves and THz communication

    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
    preconnect
    2.52
    리티
    2.43
    rom
    2.18
    స్‌
    2.15
    cious
    2.14
    shaft
    2.10
    turn
    2.09
    
    2.09
    lith
    2.07
    select
    2.04
    POSITIVE LOGITS
    ים
    2.45
    años
    2.40
    יא
    2.31
    บัญ
    2.21
     samoglas
    2.17
    AddRange
    2.15
    המ
    2.15
    笆
    2.12
    込んで
    2.11
    нче
    2.11
    Activations Density 0.036%

    No Known Activations