© 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. 14521
    Prev
    Next
    INDEX
    Explanations

    user profile setting

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

    equation, energy, boundary conditions

    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
     empresario
    0.48
    ப்போ
    0.47
    اداس
    0.47
     demostrar
    0.44
     হলেই
    0.43
    捺
    0.43
     empresarios
    0.43
     κυ
    0.42
    线的
    0.42
    大佬
    0.42
    POSITIVE LOGITS
     User
    0.50
    そこで
    0.45
    ༽
    0.42
     something
    0.41
    avia
    0.41
     {
    0.40
     user
    0.40
    
    0.38
     qual
    0.38
    avat
    0.37
    Activations Density 0.000%

    No Known Activations