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. 17-GEMMASCOPE-2-RES-65K
    4. 46996
    Prev
    Next
    INDEX
    Explanations

    and businesses, is intended

    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_17_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
     Pokud
    1.38
     QnrB
    1.27
     femora
    1.26
     inhomogeneity
    1.26
     ablation
    1.24
    /'+
    1.23
     Iter
    1.23
    koliko
    1.23
     huv
    1.22
     IMEI
    1.21
    POSITIVE LOGITS
    is
    1.39
    will
    1.01
    සර
    0.97
    t
    0.95
    로
    0.94
     
    0.91
     gonna
    0.90
    ిక
    0.87
    Welcome
    0.87
    та
    0.84
    Activations Density 0.013%

    No Known Activations