© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    positive descriptors, yet conjunctions

    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
     phenomena
    0.74
    ต่างๆ
    0.74
     різних
    0.73
    ώσεις
    0.73
    ographies
    0.73
    /;
    0.72
     সমূহ
    0.69
     techniques
    0.69
    بيقات
    0.69
    ه‌ها
    0.69
    POSITIVE LOGITS
     yet
    1.47
    Yet
    1.38
    yet
    1.24
     Yet
    1.17
     efficient
    0.96
    且
    0.96
     elegant
    0.94
     অথচ
    0.94
    而
    0.92
    efficient
    0.90
    Activations Density 0.267%

    No Known Activations