© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10467
    Prev
    Next
    INDEX
    Explanations

    complex systems and logic

    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
    Not in Any Lists

    No Comments

    Negative Logits
    banam
    1.32
    FTP
    1.32
    それでは
    1.29
     অনুসারে
    1.21
    ТО
    1.21
    હિ
    1.15
    永遠
    1.15
    ṃ
    1.15
    堅持
    1.14
    ディスク
    1.14
    POSITIVE LOGITS
     υ
    1.11
     matter
    1.08
    ^{+
    1.08
     particip
    1.04
     φω
    1.01
     под
    1.01
     Matter
    0.99
     মুখ্য
    0.98
     του
    0.98
     dessa
    0.97
    Activations Density 0.000%

    No Known Activations