© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9420
    Prev
    Next
    INDEX
    Explanations

    building construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FTWARE
    0.81
    ０
    0.68
    нали
    0.67
    廼
    0.67
    alysis
    0.66
    '></
    0.66
    ჯგუფი
    0.64
    FREQUENCY
    0.63
    潘
    0.63
    ข้อง
    0.63
    POSITIVE LOGITS
    buildings
    1.12
     buildings
    1.08
     skyscrapers
    0.99
     edificios
    0.95
     edifici
    0.94
     erected
    0.94
     Buildings
    0.94
    Buildings
    0.93
     Skyscrapers
    0.89
     edificio
    0.88
    Activations Density 0.113%

    No Known Activations