© 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. 109528
    Prev
    Next
    INDEX
    Explanations

    contextualizing specific entities

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

    maintains original structure

    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
    人文
    0.51
     প্রয়োগ
    0.47
    
    0.47
    ៖
    0.46
    는지
    0.45
     እነዚህ
    0.44
     možda
    0.43
     CREATE
    0.43
    ব্রত
    0.42
    ल्यावर
    0.42
    POSITIVE LOGITS
     liik
    0.46
    失
    0.44
     subscript
    0.43
    heat
    0.42
    观众
    0.41
     ام
    0.40
     itens
    0.40
    sections
    0.39
     zuz
    0.39
    parts
    0.39
    Activations Density 0.001%

    No Known Activations