© 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. 28530
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and proper nouns

    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
     European
    0.39
     Rein
    0.39
     Mesopotamia
    0.38
     Kirk
    0.37
    まして
    0.37
     ملي
    0.37
     l
    0.36
    pm
    0.36
     Fal
    0.35
     Assad
    0.35
    POSITIVE LOGITS
    %。
    0.48
    ะนั้น
    0.46
     күзгү
    0.45
    .​​
    0.43
     божомол
    0.42
    éticos
    0.41
     препят
    0.41
    .~
    0.41
    /).
    0.41
    疑问
    0.41
    Activations Density 0.000%

    No Known Activations