© 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. 201910
    Prev
    Next
    INDEX
    Explanations

    freedom of portability

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

    machine learning model 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
    れている
    0.41
     ()=>{
    0.41
    мережа
    0.40
     자신
    0.38
     दूसरे
    0.37
     independently
    0.37
     മരണ
    0.36
     pretty
    0.36
     independent
    0.36
     останов
    0.36
    POSITIVE LOGITS
    フル
    0.52
    装
    0.51
    数百
    0.50
     inicio
    0.49
    ཿ
    0.48
     publicación
    0.48
     adulto
    0.48
     publicar
    0.48
     arranque
    0.48
     Igu
    0.48
    Activations Density 0.002%

    No Known Activations