© 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. 87981
    Prev
    Next
    INDEX
    Explanations

    specific descriptors in lists

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

    constructed illusion

    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
     одну
    0.50
    ના
    0.48
    萜
    0.47
    能够在
    0.47
     તેણે
    0.47
    ía
    0.46
    endroit
    0.46
     તેમણે
    0.46
    Brad
    0.45
    ཁ
    0.44
    POSITIVE LOGITS
     evid
    0.48
     Portrait
    0.48
     saling
    0.48
     SWOT
    0.48
     mastery
    0.46
    ع
    0.46
     ص
    0.45
     fallacy
    0.45
    portrait
    0.44
    cul
    0.44
    Activations Density 0.002%

    No Known Activations