© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1124
    Prev
    Next
    INDEX
    Explanations

    world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nf
    0.82
    포
    0.76
     Sus
    0.75
    Sus
    0.71
    Nas
    0.67
    Ná
    0.67
    패
    0.67
    棗
    0.64
    노
    0.62
    Retention
    0.62
    POSITIVE LOGITS
     world
    3.64
     World
    3.34
    world
    3.33
    World
    3.24
     mundo
    3.23
     WORLD
    3.14
     monde
    3.07
     mondo
    3.04
    WORLD
    3.03
     wereld
    2.94
    Activations Density 0.481%

    No Known Activations