© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12731
    Prev
    Next
    INDEX
    Explanations

    error and result outcomes

    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
    Negative Logits
     balk
    1.01
    喪
    0.98
     condos
    0.96
    ]。
    0.94
     videot
    0.93
    izes
    0.93
     analogs
    0.93
     তলায়
    0.92
    izu
    0.88
    iz
    0.87
    POSITIVE LOGITS
     европей
    1.31
     Gaul
    1.26
     Fleming
    1.23
    пы
    1.20
    உலக
    1.19
     Ř
    1.19
     Europ
    1.18
    UnifiedTopology
    1.18
     Großbritannien
    1.18
    ước
    1.17
    Activations Density 0.005%

    No Known Activations