© 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. 16205
    Prev
    Next
    INDEX
    Explanations

    Arabic and non-English script

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

    no electrons emitted

    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
    짊
    0.52
    тика
    0.48
    िन
    0.45
     reconnu
    0.44
    んな
    0.44
     hidrául
    0.43
    жі
    0.43
    izada
    0.42
    étrico
    0.42
    pSensor
    0.42
    POSITIVE LOGITS
     သ
    0.51
     borrowed
    0.48
     mode
    0.48
    តែ
    0.46
     first
    0.45
    nya
    0.45
    不过
    0.45
     preparatory
    0.43
    mode
    0.43
    ';",
    0.43
    Activations Density 0.002%

    No Known Activations