© 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. 55547
    Prev
    Next
    INDEX
    Explanations

    compliance with terms and regulations

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

    AI Machines, containers, Thread

    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
    繽
    0.48
     começando
    0.44
    緩
    0.44
     PROCESSING
    0.44
     inklusive
    0.43
     bolj
    0.43
    巒
    0.43
    ?,?,
    0.42
     Verarbeitung
    0.42
     বেলা
    0.41
    POSITIVE LOGITS
    iede
    0.50
    ide
    0.50
    usz
    0.48
    idae
    0.47
    fin
    0.46
    uah
    0.46
    isor
    0.46
     Baxter
    0.46
    im
    0.45
    idah
    0.45
    Activations Density 0.000%

    No Known Activations