© 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. 14717
    Prev
    Next
    INDEX
    Explanations

    defend, seven, bill, Sun, bring

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

    0 and 1 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
    越大
    0.40
     मिळाले
    0.38
     इनको
    0.37
    regional
    0.36
    াল
    0.36
     کنید
    0.36
    width
    0.36
    <unused360>
    0.36
     новые
    0.35
    levels
    0.35
    POSITIVE LOGITS
     saludar
    0.40
     wichtig
    0.37
     langu
    0.36
     propriétaire
    0.36
     comprov
    0.36
     earnest
    0.36
     Wurzel
    0.36
     erne
    0.36
     kembali
    0.35
     notorious
    0.35
    Activations Density 0.000%

    No Known Activations