© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32874
    Prev
    Next
    INDEX
    Explanations

    courses after tables

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

    explains concepts or differentiates items

    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
     think
    0.45
    他の
    0.42
    추
    0.42
    begin
    0.41
     =
    0.39
     birth
    0.39
    think
    0.39
    birth
    0.39
    :)
    0.39
    ]
    0.39
    POSITIVE LOGITS
    汛
    0.48
     सिंचाई
    0.46
     genau
    0.45
     Rehabilitation
    0.43
    𝙞
    0.43
    hões
    0.42
     ফট
    0.42
    ..--..--
    0.42
    滿足
    0.41
     السلط
    0.41
    Activations Density 0.000%

    No Known Activations