© 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. 18768
    Prev
    Next
    INDEX
    Explanations

    relationship identifiers

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

    describing actions, concepts, or entities

    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
    тик
    0.52
     musste
    0.50
     stir
    0.46
    ল
    0.46
     tuleb
    0.44
    ալ
    0.44
    น
    0.44
    ク
    0.43
    raim
    0.42
    ਤ
    0.42
    POSITIVE LOGITS
     પોલી
    0.51
     प्रश्नावली
    0.50
     제목
    0.50
     직선
    0.50
     листа
    0.49
     આવા
    0.49
     cuestión
    0.49
     تصور
    0.49
     знак
    0.48
     сово
    0.48
    Activations Density 0.000%

    No Known Activations