© 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. 245860
    Prev
    Next
    INDEX
    Explanations

    legitimate interests. corruption

    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
     न्यायिक
    0.46
    aszt
    0.46
     Ц
    0.46
     CRED
    0.44
     Stimme
    0.44
     FRE
    0.44
     निर्माता
    0.44
    }`);
    0.44
     HARD
    0.43
    বার
    0.43
    POSITIVE LOGITS
    的过程
    0.51
    ছাড়া
    0.50
    的操作
    0.49
    ၊
    0.48
     الأع
    0.45
     Theresa
    0.45
    ο
    0.44
    的标准
    0.43
    、「
    0.43
    为其
    0.43
    Activations Density 0.001%

    No Known Activations