© 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. 161680
    Prev
    Next
    INDEX
    Explanations

    management, delivery, event

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

    data science and machine learning

    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
     तथ्यों
    0.51
     وهم
    0.51
     deception
    0.48
    ం
    0.47
    ပ်
    0.46
    ebi
    0.45
    ategy
    0.44
    Calculation
    0.44
     decommissioning
    0.44
     Girlfriend
    0.44
    POSITIVE LOGITS
     quadrato
    0.45
    Бе
    0.44
     Controle
    0.43
     Controls
    0.43
     knob
    0.43
     contatto
    0.43
     Drs
    0.42
    Су
    0.42
    敦煌
    0.42
    搂
    0.41
    Activations Density 0.001%

    No Known Activations