© 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. 7741
    Prev
    Next
    INDEX
    Explanations

    while or after

    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
    ."
    0.39
    .“
    0.37
    .”
    0.35
    .
    0.33
    ".
    0.32
    apatkan
    0.31
    ️
    0.31
    .</
    0.30
    ）.
    0.30
     właśnie
    0.30
    POSITIVE LOGITS
     प्रोटीन
    0.35
     détermine
    0.33
     entweder
    0.33
    하거나
    0.32
     দেবতা
    0.32
     ἢ
    0.32
     structs
    0.31
    結合
    0.31
    度和
    0.30
    あるいは
    0.30
    Activations Density 0.451%

    No Known Activations