© 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. 7171
    Prev
    Next
    INDEX
    Explanations

    matches the criteria

    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
    谑
    0.37
     slučaju
    0.36
     للأ
    0.35
     finement
    0.34
     untuk
    0.34
    强大的
    0.34
     তাহা
    0.33
    উৎ
    0.33
    ᴙ
    0.33
     مره
    0.32
    POSITIVE LOGITS
     aforementioned
    1.33
     उपरोक्त
    1.33
    上述
    1.31
    上記の
    1.23
     these
    1.23
     उक्त
    1.21
    上記
    1.13
    these
    1.11
     aforesaid
    1.06
    これらの
    1.05
    Activations Density 0.437%

    No Known Activations