© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15109
    Prev
    Next
    INDEX
    Explanations

    combinations and pairs

    np_acts-logits-general · gemini-2.5-flash-lite

    pairs and combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outras
    0.41
     পুঁজিব
    0.40
    䟝
    0.40
     alguno
    0.40
    мулятор
    0.39
    ("");
    0.39
     اسمه
    0.39
    邗
    0.39
     tradiciones
    0.39
    运输
    0.38
    POSITIVE LOGITS
     Kombination
    0.53
     vice
    0.50
     respectively
    0.46
    combination
    0.45
    pair
    0.44
     consiste
    0.44
     combinations
    0.44
    組み合わせ
    0.44
    同様
    0.43
    same
    0.43
    Activations Density 0.345%

    No Known Activations