© 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. 15520
    Prev
    Next
    INDEX
    Explanations

    So Israeli

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

    and so

    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
     منذ
    0.41
     since
    0.40
     license
    0.40
     八
    0.40
     dnia
    0.40
     אם
    0.40
     gdyż
    0.40
     ……
    0.40
     probation
    0.39
     denna
    0.39
    POSITIVE LOGITS
    そういう
    0.49
    こだわ
    0.46
    굉장
    0.46
    ஜி
    0.45
    ज
    0.44
    де
    0.44
     invariably
    0.43
    am
    0.42
    у
    0.42
    जी
    0.41
    Activations Density 0.105%

    No Known Activations