© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43288
    Prev
    Next
    INDEX
    Explanations

    melt your ice

    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
    corpus
    0.47
    <unused35>
    0.47
     Pero
    0.45
    Thumbnail
    0.44
     Bald
    0.44
     ഇടപെ
    0.44
     ብዙውን
    0.43
     მიმოწერა
    0.43
     பெறும்
    0.42
    💉
    0.42
    POSITIVE LOGITS
     निर्मला
    0.46
    ῇ
    0.43
    𝘀
    0.43
    щать
    0.42
    𝗶
    0.42
    𝗜
    0.42
    䧏
    0.41
     nonzero
    0.41
    юць
    0.41
    िलं
    0.41
    Activations Density 0.001%

    No Known Activations