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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 247534
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    i
    0.55
     l
    0.52
     skr
    0.49
     (%
    0.49
     toto
    0.45
     f
    0.44
     Europ
    0.44
     entonces
    0.44
     ST
    0.43
     t
    0.43
    POSITIVE LOGITS
    rouw
    0.48
     inclusions
    0.46
    ministrazione
    0.45
     εγκα
    0.45
    ujący
    0.44
     বিশেষজ্ঞ
    0.44
    본
    0.44
    插件
    0.44
     ምክንያት
    0.43
    帮助
    0.43
    Activations Density 0.007%

    No Known Activations