© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3898
    Prev
    Next
    INDEX
    Explanations

    helper functions modules services

    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
    Negative Logits
    iti
    1.47
    neys
    1.46
    ld
    1.40
    ra
    1.38
    iru
    1.37
    غا
    1.36
    odes
    1.35
    tez
    1.34
    okban
    1.34
    ള
    1.34
    POSITIVE LOGITS
     часа
    1.58
    eaa
    1.57
     关于
    1.53
    ，$
    1.51
     wrapped
    1.51
     จํา
    1.47
     令
    1.44
     而且
    1.44
     从
    1.42
    咛
    1.40
    Activations Density 0.000%

    No Known Activations