© 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. 18166
    Prev
    Next
    INDEX
    Explanations

    SI units or scientific notation

    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
    ด
    0.42
    ាម
    0.41
     вироб
    0.40
     المركز
    0.38
    Emotional
    0.38
    Boost
    0.38
    📏
    0.38
    mvnrepository
    0.37
     ჰ
    0.37
     शह
    0.37
    POSITIVE LOGITS
     SI
    0.65
     Si
    0.56
     si
    0.56
     broker
    0.46
    si
    0.46
    Si
    0.46
     SIS
    0.45
    SI
    0.45
    एसआई
    0.43
     FIF
    0.42
    Activations Density 0.000%

    No Known Activations