© 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. 33206
    Prev
    Next
    INDEX
    Explanations

    nominal shipping

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

    negation or absence

    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
    でしたが
    0.44
    getContentPane
    0.41
     있지만
    0.41
     রুশ
    0.40
     முன்னாள்
    0.40
     );
    0.39
     প্রাক্তন
    0.39
    しましたが
    0.39
    esterday
    0.39
    {
    0.39
    POSITIVE LOGITS
     tanpa
    0.59
     respectful
    0.58
     وليس
    0.52
     wholeheartedly
    0.51
     irrespective
    0.50
     keinen
    0.49
     memastikan
    0.48
     möglichst
    0.48
     without
    0.47
     zonder
    0.47
    Activations Density 0.000%

    No Known Activations