© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55782
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    したのが
    -1.05
    手续
    -0.97
    頂いた
    -0.97
     estético
    -0.94
     marcado
    -0.92
    していますが
    -0.89
     has
    -0.87
     框
    -0.87
    内容は
    -0.87
    兩個
    -0.86
    POSITIVE LOGITS
    `;
    1.16
     a
    1.09
     into
    1.08
    :${
    1.06
     به‌عنوان
    1.05
    }
    0.98
     BETWEEN
    0.96
    mbal
    0.95
     violon
    0.94
    ALPHA
    0.94
    Activations Density 0.039%

    No Known Activations