© 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. 7-GEMMASCOPE-2-RES-16K
    7. 61
    Prev
    Next
    INDEX
    Explanations

    words ending in s

    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_7_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
     effecting
    1.06
     τ
    1.04
     bold
    1.00
     discontinu
    0.98
     fail
    0.97
     ο
    0.97
     tc
    0.96
     σ
    0.96
     hinder
    0.96
     affect
    0.94
    POSITIVE LOGITS
    ětí
    1.21
    tay
    1.18
    học
    1.17
    ramique
    1.16
    eské
    1.16
    jež
    1.12
    ření
    1.12
    leszt
    1.12
    poč
    1.11
    sberg
    1.11
    Activations Density 1.179%

    No Known Activations