© 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. 126218
    Prev
    Next
    INDEX
    Explanations

    common phrases after words

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

    frequency affects, Facebook events

    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
    to
    0.50
    ट्
    0.44
    a
    0.43
     khô
    0.41
     chút
    0.40
     Ly
    0.40
    ta
    0.40
    某个
    0.38
    ty
    0.38
    的上
    0.38
    POSITIVE LOGITS
     कुटुंबा
    0.49
     परिवार
    0.48
    濫
    0.47
     വീട്ട
    0.47
     समाजा
    0.46
     Ди
    0.45
     সাজ
    0.45
     является
    0.45
     شدہ
    0.45
    АЗ
    0.45
    Activations Density 0.000%

    No Known Activations