© 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. 237678
    Prev
    Next
    INDEX
    Explanations

    investigating engineering luxury property

    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
    tki
    0.48
     এতো
    0.47
     रूई
    0.47
    Dataset
    0.47
    dataset
    0.47
     टेबल
    0.46
     स्वतंत्र
    0.46
    𝚛
    0.46
    thead
    0.46
    Algorithm
    0.45
    POSITIVE LOGITS
     частини
    0.47
     Partei
    0.41
    傭
    0.41
     gekauft
    0.41
    범
    0.41
    戰
    0.41
     pension
    0.41
     moulded
    0.40
     dollar
    0.40
    Chill
    0.39
    Activations Density 0.000%

    No Known Activations