© 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. 201113
    Prev
    Next
    INDEX
    Explanations

    recommendations for fuel

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

    gentle, curious, herd animals

    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
    䔋
    0.55
     ინტერ
    0.52
     narcot
    0.50
    automatic
    0.50
     benutzt
    0.49
    landish
    0.49
    とっても
    0.49
    こうした
    0.48
     اجتما
    0.47
     آزمایش
    0.47
    POSITIVE LOGITS
    0.47
    ිරි
    0.47
    ည့်
    0.45
    沟
    0.45
    صف
    0.43
     doba
    0.42
    ضيع
    0.42
    
    0.42
    աս
    0.40
    '
    0.40
    Activations Density 0.001%

    No Known Activations