© 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. 161201
    Prev
    Next
    INDEX
    Explanations

    copper mining, cost location

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

    take over the world

    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
    τροπ
    0.48
    μ
    0.47
    φ
    0.47
    dsale
    0.45
    मा
    0.45
    imwrite
    0.43
     Carnaval
    0.43
    🥑
    0.43
    ढ़ा
    0.43
    ラック
    0.43
    POSITIVE LOGITS
     ইতিহাসের
    0.44
     kling
    0.44
     прибли
    0.44
    in
    0.44
     ני
    0.43
     besonder
    0.43
    น้อง
    0.43
     потен
    0.42
     bau
    0.42
    徫
    0.42
    Activations Density 0.000%

    No Known Activations