© 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-262K
    7. 40053
    Prev
    Next
    INDEX
    Explanations

    data structures and programming concepts

    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_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
    ו
    0.48
    Ո
    0.47
    畫面
    0.47
    라
    0.47
    부
    0.46
    乨
    0.45
    τική
    0.45
    䡏
    0.45
    മ്പ്
    0.44
    끼
    0.44
    POSITIVE LOGITS
     YAML
    0.42
     such
    0.41
     XML
    0.40
     awk
    0.40
     prag
    0.38
     occasionally
    0.38
     constrained
    0.37
     JSON
    0.37
     Shen
    0.37
     VL
    0.37
    Activations Density 0.002%

    No Known Activations