© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25904
    Prev
    Next
    INDEX
    Explanations

    internal modules

    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
    ів
    0.48
     بخاری
    0.43
    ОВ
    0.42
     beneficial
    0.39
     B
    0.38
    CO
    0.38
     Kingdom
    0.37
     Để
    0.37
     الك
    0.37
    我就
    0.37
    POSITIVE LOGITS
    ndan
    0.45
    zigzag
    0.44
    тыми
    0.44
    คโนโลยี
    0.44
    axaca
    0.43
     \%(
    0.42
    モード
    0.42
    Zip
    0.41
    மன்
    0.41
    𝖔
    0.41
    Activations Density 0.000%

    No Known Activations