© 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. 2033
    Prev
    Next
    INDEX
    Explanations

    code package declaration

    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
    augh
    0.42
    Û
    0.42
    boxed
    0.41
    QRect
    0.40
    ‖</
    0.38
     circunfer
    0.38
    énés
    0.38
    绎
    0.38
    Ţ
    0.38
     lapply
    0.37
    POSITIVE LOGITS
    package
    0.51
    controllers
    0.47
     Utils
    0.46
     utils
    0.45
     util
    0.43
     controllers
    0.43
     java
    0.42
     Jakarta
    0.40
    practice
    0.40
    ட்டை
    0.40
    Activations Density 0.017%

    No Known Activations