© 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-262K
    7. 20847
    Prev
    Next
    INDEX
    Explanations

    Android Binder IPC

    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_262k_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
    Formula
    0.43
     luisant
    0.41
    澎
    0.41
     rumus
    0.40
    波
    0.40
    公式
    0.40
    Sim
    0.39
     Margarita
    0.39
    CASCADE
    0.39
    딛
    0.39
    POSITIVE LOGITS
     IPC
    1.16
     ipc
    1.01
    IPC
    0.96
     binder
    0.88
    ipc
    0.87
     Binder
    0.82
    Binder
    0.80
     binders
    0.79
    binder
    0.68
    messenger
    0.64
    Activations Density 0.013%

    No Known Activations