© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58610
    Prev
    Next
    INDEX
    Explanations

    posted dates

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

    aviation relies on reporting

    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_262k_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
    喡
    0.55
     потенциа
    0.52
    Potential
    0.52
    காற்று
    0.51
    读取
    0.50
    écoute
    0.50
    矨
    0.50
     diálogo
    0.50
    Ტ
    0.50
    возможно
    0.50
    POSITIVE LOGITS
     ruled
    0.58
     A
    0.56
     on
    0.54
     C
    0.52
     germ
    0.51
    ↵↵
    0.50
     O
    0.50
     G
    0.50
     equally
    0.49
     chival
    0.49
    Activations Density 0.007%

    No Known Activations