© 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. 83149
    Prev
    Next
    INDEX
    Explanations

    symbolic loading or language combines

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

    strategies, indices, and

    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
     该
    0.52
     før
    0.49
     Azer
    0.49
    ర్థిక
    0.48
    плення
    0.48
     tension
    0.47
     fondness
    0.47
     innan
    0.46
    开车
    0.46
     transmissions
    0.46
    POSITIVE LOGITS
    اي
    0.48
    یک
    0.47
     ወይም
    0.45
    (",");
    0.42
    
    0.42
    ುತ್ತೇನೆ
    0.42
    ("",
    0.41
    uslar
    0.41
    (
    0.41
    proba
    0.41
    Activations Density 0.001%

    No Known Activations