© 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. 3145
    Prev
    Next
    INDEX
    Explanations

    regarding your

    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
     multitud
    0.50
    ファイルの
    0.50
     makanan
    0.50
    インターネット
    0.45
    }%
    0.43
     સ્ટ
    0.43
     venturing
    0.43
     multinationals
    0.42
     جنگ
    0.42
    whelming
    0.42
    POSITIVE LOGITS
    다면
    0.45
    kbd
    0.40
    еме
    0.39
     thước
    0.39
    ഡോ
    0.39
     remind
    0.38
    :@
    0.38
     reminded
    0.38
    忘记
    0.38
    ፡
    0.38
    Activations Density 0.028%

    No Known Activations