© 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. 30400
    Prev
    Next
    INDEX
    Explanations

    processes and creations

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

    knowledge base creation approaches

    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
    了承
    0.47
    化した
    0.46
    叡
    0.42
     variáveis
    0.42
    ωσε
    0.41
    ز
    0.41
     stvari
    0.41
     cnpj
    0.40
    鵝
    0.40
     thereof
    0.39
    POSITIVE LOGITS
    mechanism
    0.52
    িকারী
    0.50
    trong
    0.48
     आतंकवाद
    0.46
     সক্ষম
    0.45
    ärk
    0.45
     समांतर
    0.44
    arantad
    0.44
    taining
    0.44
    dalam
    0.44
    Activations Density 0.260%

    No Known Activations