© 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. 4273
    Prev
    Next
    INDEX
    Explanations

    specific phrases and descriptions

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

    dog, cancellation, Super

    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
    認知
    0.38
     ऑनलाइन
    0.38
    <unused65>
    0.38
    ేవ
    0.37
    干部
    0.37
     प्रकल्
    0.36
     genießen
    0.36
    <unused85>
    0.35
     héros
    0.35
     داعش
    0.35
    POSITIVE LOGITS
     either
    0.38
     usually
    0.36
     becomes
    0.35
    ↵
    0.35
      
    0.35
     something
    0.34
     University
    0.34
     as
    0.34
     International
    0.33
     चूंकि
    0.33
    Activations Density 0.078%

    No Known Activations