Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7278
    Prev
    Next
    INDEX
    Explanations

    future action

    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_16k_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
    Untuk
    0.83
     france
    0.83
    untuk
    0.81
    வா
    0.80
    से
    0.75
    []
    0.73
     kaya
    0.73
     यामध्ये
    0.72
    या
    0.72
    ōn
    0.71
    POSITIVE LOGITS
     peculiarities
    1.09
     Somebody
    1.03
     („
    1.00
    wyczaj
    0.98
     Everybody
    0.97
     तकरीबन
    0.97
     Nowadays
    0.97
     researches
    0.96
     advices
    0.94
    Т
    0.94
    Activations Density 0.001%

    No Known Activations