© 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. 16-GEMMASCOPE-2-RES-262K
    7. 40804
    Prev
    Next
    INDEX
    Explanations

    factory initialization

    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_16_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
    P
    0.74
    م
    0.74
    B
    0.70
    ↵↵
    0.68
    Г
    0.68
    ل
    0.67
    平
    0.63
    Code
    0.61
    机遇
    0.61
     by
    0.61
    POSITIVE LOGITS
    amas
    0.63
    enciais
    0.62
    erno
    0.56
     respet
    0.55
    ının
    0.53
    asso
    0.53
    si
    0.53
    skoj
    0.52
    𝘴
    0.52
    sama
    0.52
    Activations Density 0.000%

    No Known Activations