© 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. 190353
    Prev
    Next
    INDEX
    Explanations

    Internet cancellation product building centuries celebrity

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

    entity followed by descriptor

    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
    lore
    0.49
    scorer
    0.48
    鎶
    0.47
    perturbed
    0.47
     puree
    0.47
     thermostats
    0.47
    cleaned
    0.46
    anjang
    0.45
    efficiency
    0.44
    owanym
    0.44
    POSITIVE LOGITS
    จะ
    0.48
     Sustainable
    0.46
     Veh
    0.46
    。《
    0.45
    踐
    0.45
    จะไม่
    0.44
    ة
    0.44
     কিছুই
    0.44
     Verg
    0.44
     Disabilities
    0.43
    Activations Density 0.001%

    No Known Activations