© 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-16K
    7. 3274
    Prev
    Next
    INDEX
    Explanations

    code variables and constructs

    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
    aldi
    0.48
     расстояние
    0.46
    ডিও
    0.44
    流量
    0.42
     громадян
    0.41
     لکھا
    0.41
    ähn
    0.41
    /*',
    0.40
    belum
    0.40
    itung
    0.39
    POSITIVE LOGITS
     Misalnya
    0.41
     Comes
    0.39
     chosen
    0.38
    比如說
    0.37
     Se
    0.36
     مثلا
    0.36
     Sw
    0.35
     Samb
    0.35
     Beth
    0.35
     Collo
    0.34
    Activations Density 0.435%

    No Known Activations