© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47381
    Prev
    Next
    INDEX
    Explanations

    new then

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

    numbers and buying

    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
     yanı
    0.52
     instância
    0.45
     velocità
    0.44
    襁
    0.44
     VLC
    0.44
    zinho
    0.43
     herhangi
    0.42
     clínicos
    0.42
     spécifique
    0.42
     Vanuatu
    0.42
    POSITIVE LOGITS
     দত্ত
    0.44
     aircraft
    0.41
    跡
    0.41
     cartridges
    0.41
     oblong
    0.40
    खान
    0.40
     ships
    0.40
     figs
    0.40
     elections
    0.38
     cancers
    0.38
    Activations Density 0.000%

    No Known Activations