© 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. 12589
    Prev
    Next
    INDEX
    Explanations

    geographic directions and locations

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

    regions and directions

    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
    6
    0.66
    8
    0.57
    0
    0.54
    9
    0.51
    കൾ
    0.50
    4
    0.50
     Angeb
    0.50
    7
    0.48
     neki
    0.45
     Barangay
    0.45
    POSITIVE LOGITS
    most
    0.56
     eastern
    0.47
     planks
    0.47
     litoral
    0.44
    Western
    0.43
    defined
    0.43
     hemisphere
    0.42
    portions
    0.42
     occidental
    0.42
    ia
    0.42
    Activations Density 0.066%

    No Known Activations