© 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-65K
    7. 165
    Prev
    Next
    INDEX
    Explanations

    what phrases

    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_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
    การ
    1.07
     for
    1.05
     by
    1.00
     ने
    0.93
     कोणत्याही
    0.93
    ა
    0.93
    ino
    0.93
     आंकड़ों
    0.92
    𝙙
    0.89
     د
    0.88
    POSITIVE LOGITS
    t
    1.74
    p
    1.29
    。
    1.27
    n
    1.24
    to
    1.20
    y
    1.18
    ।
    1.17
    কে
    1.14
    }";
    1.10
    i
    1.10
    Activations Density 1.279%

    No Known Activations