© 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. 151722
    Prev
    Next
    INDEX
    Explanations

    mobile crushing plant

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

    can see or be

    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
    घी
    0.46
    மிகு
    0.46
     Zustand
    0.46
     chức
    0.46
    ில்லியன்
    0.46
     Últ
    0.46
    窍
    0.46
     Giuliani
    0.45
     Campe
    0.45
     yüzde
    0.45
    POSITIVE LOGITS
     王
    0.47
     黄
    0.45
    禁
    0.45
    STER
    0.44
    Stewart
    0.43
    シャン
    0.42
    煙
    0.42
     zlat
    0.42
    王
    0.41
     九
    0.41
    Activations Density 0.000%

    No Known Activations