© 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. 40-GEMMASCOPE-2-RES-65K
    7. 706
    Prev
    Next
    INDEX
    Explanations

    let me do something

    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_40_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
     veuillez
    0.21
     concurrent
    0.19
    以免
    0.18
    /
    0.18
     Reliance
    0.18
    これは
    0.18
    ↵↵
    0.18
     및
    0.18
     اکثر
    0.18
     concluding
    0.18
    POSITIVE LOGITS
     things
    0.38
     everything
    0.36
    things
    0.35
     nobody
    0.33
     everyone
    0.32
     THINGS
    0.32
    nobody
    0.31
     somebody
    0.29
    Things
    0.29
     qualcosa
    0.29
    Activations Density 0.658%

    No Known Activations