© 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. 138902
    Prev
    Next
    INDEX
    Explanations

    actions like division or removal

    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
     นี่
    0.46
    棭
    0.45
    Kid
    0.44
     Από
    0.44
     Якщо
    0.43
     প্রিন
    0.43
    Ee
    0.42
     Кре
    0.42
    粓
    0.42
    Todo
    0.42
    POSITIVE LOGITS
     losing
    0.47
     loses
    0.42
     socialists
    0.41
     inflex
    0.40
     veterans
    0.40
     vocalist
    0.40
    ġ
    0.40
     نظ
    0.39
    Â
    0.39
     scar
    0.39
    Activations Density 0.004%

    No Known Activations