© 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. 179328
    Prev
    Next
    INDEX
    Explanations

    compound noun phrases

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

    characteristics of open-source AI

    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
    変化
    0.67
     процессе
    0.50
    締め
    0.50
    病人
    0.48
     आसान
    0.47
    課程
    0.47
     итоге
    0.47
    仕
    0.47
    総合
    0.46
    ISTIC
    0.46
    POSITIVE LOGITS
     Pov
    0.50
     Publicity
    0.50
     Sh
    0.49
     Range
    0.49
     Mew
    0.48
     Open
    0.47
     Luke
    0.47
     Fans
    0.47
     Bias
    0.46
     Theta
    0.46
    Activations Density 0.000%

    No Known Activations