© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    mobile applications and payments

    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
    getchar
    2.34
     ‘
    2.17
     EventArgs
    2.08
     internals
    2.05
     ['',
    2.01
     Länder
    1.99
     Ancient
    1.99
    鞅
    1.98
     NSError
    1.97
    ibernate
    1.96
    POSITIVE LOGITS
    ubes
    2.54
    ЛЬ
    2.38
    ffer
    2.37
     불구
    2.35
    ANCES
    2.34
    ffes
    2.26
    ्यर
    2.24
    cker
    2.20
    चाप
    2.19
    ricies
    2.13
    Activations Density 0.041%

    No Known Activations