© 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. 190226
    Prev
    Next
    INDEX
    Explanations

    descriptions of states or abstract concepts

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

    list components and structure

    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
    a
    0.51
    आ
    0.50
    lari
    0.49
     formazione
    0.49
     formação
    0.49
    ه
    0.48
    1
    0.47
    ایه
    0.47
    आज
    0.46
    जन
    0.46
    POSITIVE LOGITS
     ಸಾಧ
    0.45
    (".",
    0.45
     Corolle
    0.44
     തമ്മ
    0.44
    紶
    0.43
     torches
    0.42
     যুদ্ধ
    0.42
     majú
    0.42
    諰
    0.42
    archiwizowane
    0.41
    Activations Density 0.001%

    No Known Activations