© 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. 113621
    Prev
    Next
    INDEX
    Explanations

    invoice will

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

    explain **because**

    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
     топлива
    0.52
    ри
    0.49
     труб
    0.48
     масла
    0.47
     Kesehatan
    0.46
    🥇
    0.46
     strtoupper
    0.45
     туда
    0.45
     Src
    0.44
     hendak
    0.43
    POSITIVE LOGITS
    的要求
    0.49
    书
    0.46
    不会
    0.46
    विशेष
    0.46
    的名
    0.45
     encouragement
    0.44
     conséquences
    0.44
    孬
    0.43
    的影响
    0.43
    影响
    0.42
    Activations Density 0.000%

    No Known Activations