© 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. 72984
    Prev
    Next
    INDEX
    Explanations

    carrier liability loss

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

    directly into, inspect, Angiotensin

    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
    ర్చు
    0.57
    र्नर
    0.51
    uwa
    0.49
     пыта
    0.43
    试
    0.43
    Pets
    0.42
    ர்
    0.42
    满足
    0.42
    政治
    0.41
    рав
    0.41
    POSITIVE LOGITS
     arrays
    0.52
     ကု
    0.52
     អ
    0.49
     آج
    0.48
     でも
    0.48
     बनाये
    0.48
    cyj
    0.48
    entered
    0.48
    flickr
    0.47
    ก่อน
    0.47
    Activations Density 0.000%

    No Known Activations