© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 476
    Prev
    Next
    INDEX
    Explanations

    entity discovers hidden information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
    说了
    0.92
    ありました
    0.82
    ませんでした
    0.81
     있었다
    0.78
    かったです
    0.76
    がありました
    0.74
    了一声
    0.74
    셨
    0.73
     હતું
    0.73
    ிருந்தது
    0.72
    POSITIVE LOGITS
     discovers
    1.09
     becomes
    1.09
     proves
    1.04
     convinces
    0.94
     realizes
    0.91
     finds
    0.91
     begins
    0.91
     Discover
    0.91
     discover
    0.91
    Discover
    0.89
    Activations Density 0.024%

    No Known Activations