© 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. 175100
    Prev
    Next
    INDEX
    Explanations

    locations, then numbers

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

    disagreement or agreement fragments

    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
     दर्शक
    0.45
    EOUT
    0.42
    觀眾
    0.42
    禳
    0.42
    Manual
    0.41
    Together
    0.41
    的故事
    0.41
    辙
    0.40
    銠
    0.40
    なので
    0.40
    POSITIVE LOGITS
     opérations
    0.46
    emin
    0.45
    yg
    0.45
     معرف
    0.44
     повністю
    0.44
     excer
    0.44
    elb
    0.43
    igers
    0.43
    ichar
    0.43
     hydrogenation
    0.42
    Activations Density 0.003%

    No Known Activations