© 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. 120696
    Prev
    Next
    INDEX
    Explanations

    lawyer evaluations

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

    magnetic fields

    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
     calcio
    0.55
     बाती
    0.52
    StillWater
    0.49
    蜊
    0.46
    ඤ
    0.46
     límites
    0.45
    ພາ
    0.45
    கல்
    0.45
    
    0.45
    娱乐圈
    0.45
    POSITIVE LOGITS
    don
    0.45
    Magnetic
    0.42
     configuration
    0.42
     configurations
    0.41
    HS
    0.41
     duplic
    0.40
     ሞ
    0.40
    回
    0.40
     onload
    0.39
    dream
    0.39
    Activations Density 0.000%

    No Known Activations