© 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. 64989
    Prev
    Next
    INDEX
    Explanations

    towers and lighthouses

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

    lighthouse keeper

    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
     учреждений
    0.43
    ৃঙ্খলা
    0.43
    たたみ
    0.43
    vá
    0.42
     रचनात्मक
    0.42
    街
    0.41
    滚动
    0.41
    法令
    0.41
    巷
    0.41
     পছ
    0.41
    POSITIVE LOGITS
     tower
    1.16
     towers
    1.00
     torre
    0.95
    Tower
    0.91
    tower
    0.91
     Tower
    0.88
     lighthouse
    0.85
    lighthouse
    0.81
     Lighthouse
    0.76
    🗼
    0.75
    Activations Density 0.099%

    No Known Activations