© 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. 414
    Prev
    Next
    INDEX
    Explanations

    python code

    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
     tap
    0.68
     (+
    0.65
    dressing
    0.65
    tart
    0.64
    pressing
    0.63
    stress
    0.61
    while
    0.61
     (
    0.61
    press
    0.60
     escort
    0.60
    POSITIVE LOGITS
     organizaciones
    1.48
     Pengembangan
    1.45
     meravigli
    1.43
     niezwy
    1.42
     categorías
    1.38
     uruch
    1.36
     realizzazione
    1.35
     jî
    1.34
     desenvolved
    1.33
     geliştir
    1.33
    Activations Density 0.043%

    No Known Activations