© 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. 97442
    Prev
    Next
    INDEX
    Explanations

    searching for info and details

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

    diverse international vocabulary

    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
    มากขึ้น
    0.49
    ванный
    0.47
    
    0.47
    ണ്യ
    0.45
    ক্সে
    0.45
    ర్కొ
    0.44
     מפ
    0.44
     itibaren
    0.43
    जुर्ग
    0.42
    🏈
    0.42
    POSITIVE LOGITS
     Ка
    0.58
    ijala
    0.57
    ived
    0.48
    ora
    0.48
    jali
    0.48
    вета
    0.48
    iva
    0.48
     пережи
    0.48
    ova
    0.48
    ig
    0.47
    Activations Density 0.000%

    No Known Activations