© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57624
    Prev
    Next
    INDEX
    Explanations

    offering or analogy

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

    describing consequences or relations

    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
    并且
    0.50
    躁
    0.45
    的时候
    0.45
    渎
    0.43
    欝
    0.42
    尤
    0.42
     करूंगा
    0.42
     عندما
    0.42
    ጉ
    0.42
    思维
    0.41
    POSITIVE LOGITS
     ofer
    0.51
     salario
    0.46
     ofrecer
    0.43
     asla
    0.42
     offrent
    0.41
     tokenize
    0.41
     salaire
    0.41
     incluem
    0.41
     cadeaux
    0.41
    apa
    0.40
    Activations Density 0.000%

    No Known Activations