© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13697
    Prev
    Next
    INDEX
    Explanations

    "you can often"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     собственно
    0.43
     fortfarande
    0.38
    GetComponents
    0.36
    льным
    0.33
    仍
    0.33
     คอม
    0.33
    可是
    0.33
     但是
    0.33
    看法
    0.33
    煽
    0.33
    POSITIVE LOGITS
    他们在
    0.48
     त्यांनी
    0.47
     Они
    0.45
     ponieważ
    0.45
     nonprofits
    0.43
     ताकि
    0.42
    这将
    0.42
     cuz
    0.41
     utilizados
    0.41
     karena
    0.41
    Activations Density 0.044%

    No Known Activations