© 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. 57670
    Prev
    Next
    INDEX
    Explanations

    introduction of definitions or explanations

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

    explaining what something refers to

    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
     Greeks
    0.49
     alebo
    0.47
     nedeniyle
    0.47
     ή
    0.46
     meaningless
    0.44
     oder
    0.44
     σημαν
    0.44
    回顾
    0.42
     Сред
    0.42
     shameful
    0.42
    POSITIVE LOGITS
    拠
    0.47
    any
    0.46
    식회사
    0.43
    ว่าจะ
    0.40
    숴
    0.38
    jski
    0.38
    的就是
    0.38
     برخور
    0.38
     любой
    0.37
     любого
    0.37
    Activations Density 0.035%

    No Known Activations