© 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. 25191
    Prev
    Next
    INDEX
    Explanations

    listing or enumerating

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

    breakdowns and lists

    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
     specifically
    0.43
    ̄
    0.43
     reimag
    0.42
    un
    0.42
     minimalistic
    0.41
     OÜ
    0.41
     repurposed
    0.40
    ij
    0.39
    primary
    0.39
     મુખ્ય
    0.39
    POSITIVE LOGITS
     acond
    0.43
    醞
    0.41
    蛋白質
    0.40
     pendiente
    0.39
    改革
    0.39
    지금
    0.39
    我知道
    0.39
     evidentemente
    0.38
     suelos
    0.38
    酝
    0.37
    Activations Density 0.000%

    No Known Activations