© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84482
    Prev
    Next
    INDEX
    Explanations

    various subjects or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     its
    -1.37
    konos
    -1.27
    ∽
    -1.15
    queryInterface
    -1.12
    Koordinaten
    -1.11
    ઁ
    -1.09
    ₫
    -1.09
    posizioni
    -1.08
    бочки
    -1.07
    ⟹
    -1.04
    POSITIVE LOGITS
    他们在
    1.17
    などを
    1.06
    色々な
    1.04
     ostat
    1.01
     '-';
    0.96
    などは
    0.96
    几种
    0.94
    向了
    0.94
     Situationen
    0.94
    bereiche
    0.93
    Activations Density 0.001%

    No Known Activations