© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 10951
    Prev
    Next
    INDEX
    Explanations

    sequence of methods

    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
     e
    0.54
     in
    0.52
     et
    0.51
     fl
    0.49
     >
    0.48
     and
    0.48
     section
    0.46
    în
    0.46
    ھ
    0.46
    گ
    0.45
    POSITIVE LOGITS
     Чтобы
    0.59
    kfollowers
    0.56
     upang
    0.54
    ដើម្បី
    0.53
    私募基金管理人
    0.52
    OfDeath
    0.48
    Чтобы
    0.48
     aby
    0.48
    เพื่อให้
    0.47
    ӹ
    0.46
    Activations Density 0.142%

    No Known Activations