© 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. 9653
    Prev
    Next
    INDEX
    Explanations

    travel to locations and directions

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

    exploring beyond the city

    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
     ফলাফল
    0.49
     हानिकारक
    0.46
     dilengkapi
    0.45
    赟
    0.45
    िकारक
    0.44
     incroy
    0.44
     tâches
    0.43
    ꉂ
    0.43
    )/(
    0.42
     அதிகரி
    0.42
    POSITIVE LOGITS
     outlying
    0.63
    郊
    0.61
     southward
    0.57
     backcountry
    0.55
     countryside
    0.54
     exploring
    0.53
     eastward
    0.52
     দক্ষিণে
    0.52
    東
    0.52
    wilderness
    0.52
    Activations Density 0.061%

    No Known Activations