© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 754
    Prev
    Next
    INDEX
    Explanations

    options or alternatives

    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_16k_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
    的時候
    0.49
    然后
    0.49
    𝟬
    0.47
    ᱐
    0.47
    นิด
    0.45
    ทั้ง
    0.45
     wszyst
    0.44
     તમામ
    0.44
    🙌
    0.43
     najważ
    0.43
    POSITIVE LOGITS
    ignal
    0.81
    ients
    0.80
     addirittura
    0.77
     यूँ
    0.64
     यूं
    0.63
    acles
    0.59
     alternatively
    0.58
    leans
    0.57
    ofacial
    0.57
     вовсе
    0.56
    Activations Density 0.617%

    No Known Activations