© 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. 14948
    Prev
    Next
    INDEX
    Explanations

    concepts and conditions

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

    scale

    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
    非常的
    0.56
     nagyon
    0.56
     очень
    0.54
    是非常
    0.50
     foarte
    0.47
     very
    0.46
     .
    0.45
     VERY
    0.45
     дуже
    0.45
    젼
    0.45
    POSITIVE LOGITS
    fulfilled
    0.52
     idk
    0.51
    揹
    0.50
    beit
    0.48
    汎
    0.48
    presentable
    0.48
    witness
    0.47
    accumulation
    0.47
    expansive
    0.46
    累積
    0.46
    Activations Density 0.014%

    No Known Activations