© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8898
    Prev
    Next
    INDEX
    Explanations

    produced or destined for use

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

    intended for

    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_40_width_16k_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
     rebuilt
    0.45
     aufgebaut
    0.42
     dibangun
    0.42
     eingerichtet
    0.40
     مبنی
    0.40
    शासित
    0.39
    棤
    0.39
     theorists
    0.38
    >::
    0.38
     build
    0.38
    POSITIVE LOGITS
     destinés
    0.92
     destined
    0.84
     destiné
    0.71
     destinée
    0.69
     destin
    0.68
     destinados
    0.68
     прода
    0.68
     using
    0.61
     usando
    0.61
     destinado
    0.61
    Activations Density 0.281%

    No Known Activations