© 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. 242927
    Prev
    Next
    INDEX
    Explanations

    locations and descriptions

    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
    で作
    0.45
     haremos
    0.44
    㙋
    0.44
     sillons
    0.43
    InitStruct
    0.43
    เขา
    0.42
     erreurs
    0.42
    รี
    0.42
     pakas
    0.41
     géographique
    0.41
    POSITIVE LOGITS
    ut
    0.50
    anticipated
    0.48
     비롯
    0.47
    incorporated
    0.45
    ͉
    0.44
     Siegel
    0.43
    uri
    0.43
     सर्वाधिक
    0.43
    uk
    0.41
    र्म
    0.41
    Activations Density 0.001%

    No Known Activations