© 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. 8545
    Prev
    Next
    INDEX
    Explanations

    strong emotional declarations

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

    secretly enjoy

    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
         
    0.52
    
    0.49
    राय
    0.48
     contributory
    0.48
     अथवा
    0.46
     quelquefois
    0.46
     sportsmen
    0.45
    
    0.45
     करीत
    0.44
     Oriental
    0.44
    POSITIVE LOGITS
     lmao
    1.16
     fucking
    1.09
     badass
    1.05
     fucked
    1.00
     fuck
    0.96
     shitty
    0.95
     freaking
    0.92
     idk
    0.92
    めっちゃ
    0.91
    fuck
    0.88
    Activations Density 0.218%

    No Known Activations