© 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. 126
    Prev
    Next
    INDEX
    Explanations

    prefix + suffix word formation

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

    proper nouns and specific entities

    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
     अधिवक्ता
    0.26
     implementación
    0.25
     ERISA
    0.25
    ভূত
    0.25
     médias
    0.25
    众
    0.24
    业务
    0.24
     руководитель
    0.24
    গ্রহায়ণ
    0.24
    <unused2175>
    0.24
    POSITIVE LOGITS
     medan
    0.25
     harus
    0.24
    山の
    0.24
    ar
    0.23
     pokemon
    0.23
     lizards
    0.23
     patio
    0.23
     haci
    0.23
     Goa
    0.22
     इलाकों
    0.22
    Activations Density 1.347%

    No Known Activations