© 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. 113216
    Prev
    Next
    INDEX
    Explanations

    Famer Allen, not available, etchings

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

    important to remember

    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
    萬
    0.46
     U
    0.44
    يكا
    0.44
    U
    0.44
     native
    0.43
    يدا
    0.43
     tenant
    0.42
    s
    0.42
     planner
    0.42
    遼
    0.42
    POSITIVE LOGITS
    
    0.53
     ря
    0.51
    ْر
    0.51
     mógł
    0.50
     curviliné
    0.48
     diperoleh
    0.48
     confidently
    0.48
    𝚑
    0.48
    <unused646>
    0.47
    铉
    0.46
    Activations Density 0.000%

    No Known Activations