© 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. 24745
    Prev
    Next
    INDEX
    Explanations

    if you, run out

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

    early day eminem peak

    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
     设置
    0.61
    Magenta
    0.48
    ärten
    0.46
    ὁ
    0.46
     πε
    0.45
    κος
    0.45
     开发
    0.45
     口
    0.44
     加
    0.44
     方法
    0.44
    POSITIVE LOGITS
     wied
    0.55
     nuestras
    0.45
    pathy
    0.45
     adhesives
    0.45
     sympathy
    0.44
     travailler
    0.43
    ânia
    0.43
     estadounidense
    0.41
    жно
    0.40
     কারণেই
    0.40
    Activations Density 0.000%

    No Known Activations