© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9972
    Prev
    Next
    INDEX
    Explanations

    October 26, 2023

    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_22_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
     Beth
    1.18
    Beth
    1.16
     hert
    1.07
     mains
    1.03
     sho
    0.99
     cardio
    0.99
     Marlow
    0.98
     ☐
    0.97
     inorder
    0.94
     sla
    0.93
    POSITIVE LOGITS
    一度
    0.94
    越
    0.86
    덮
    0.77
    이너
    0.77
     अगली
    0.76
    不久
    0.74
    几次
    0.73
    伏
    0.72
    晚
    0.72
    接近
    0.71
    Activations Density 0.005%

    No Known Activations