© 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. 150
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     que
    1.28
     Cuando
    1.14
     Ceux
    1.11
     Quando
    1.07
     если
    1.06
     (
    1.06
     якщо
    1.04
     Wenn
    1.03
     spécialement
    1.02
    (
    1.02
    POSITIVE LOGITS
     stressors
    1.24
     covariates
    1.24
     artefacts
    1.22
     comorbidities
    1.18
    asadd
    1.18
     inconven
    1.14
    atypes
    1.13
     hardships
    1.13
    ストレス
    1.12
    adə
    1.12
    Activations Density 1.222%

    No Known Activations