© 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. 36119
    Prev
    Next
    INDEX
    Explanations

    languages and specific regions

    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
     ਡ
    0.46
    ंकन
    0.46
    ခန်း
    0.45
    රක
    0.45
     внутри
    0.42
    elesen
    0.42
    asak
    0.41
    豎
    0.40
    ቝ
    0.40
    NSMutableArray
    0.39
    POSITIVE LOGITS
    2
    0.41
    ２
    0.39
     stranger
    0.39
     Lui
    0.38
     ২১
    0.37
    Ṛ
    0.37
    一些
    0.37
    依赖
    0.37
    炁
    0.37
    ږي
    0.36
    Activations Density 0.006%

    No Known Activations