© 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. 139374
    Prev
    Next
    INDEX
    Explanations

    classic. Spanish, example

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

    initialization, seeking solace, simplifies inventory

    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
     😊
    0.55
     sun
    0.54
     showroom
    0.54
     😁
    0.53
     you
    0.51
     😀
    0.51
     😄
    0.51
     Scientology
    0.50
     Christmas
    0.49
     §
    0.49
    POSITIVE LOGITS
    Medic
    0.51
    RESS
    0.51
    รรม
    0.50
    Proveedor
    0.49
    Depois
    0.46
    EVA
    0.46
    ਰ
    0.46
    OMAS
    0.46
    ರ್ಮ
    0.46
    رس
    0.45
    Activations Density 0.002%

    No Known Activations