© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 837
    Prev
    Next
    INDEX
    Explanations

    the + descriptor

    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
     other
    1.21
     we
    1.20
     OTHER
    1.19
    <0xF3>
    1.14
     motive
    1.11
     it
    1.07
     others
    1.06
     a
    1.05
     this
    1.03
     to
    1.01
    POSITIVE LOGITS
     poderoso
    1.77
     Amerikaanse
    1.71
     अंतर्राष्ट्रीय
    1.71
     statunitense
    1.71
     famed
    1.70
     dikenal
    1.69
     niezwy
    1.69
     tujuh
    1.68
     Prancis
    1.67
     internasional
    1.67
    Activations Density 0.752%

    No Known Activations