© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1966
    Prev
    Next
    INDEX
    Explanations

    is now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     बनेंगे
    0.52
     लगेगा
    0.50
    াবেন
    0.46
     आएंगी
    0.44
                       
    0.44
     बनेगा
    0.42
     পারব
    0.42
     haremos
    0.41
    무
    0.41
    マ
    0.41
    POSITIVE LOGITS
     now
    0.87
     maintenant
    0.86
     telah
    0.82
     теперь
    0.79
     ahora
    0.74
     gewesen
    0.72
     nyní
    0.71
     almış
    0.69
     இப்போது
    0.69
     अब
    0.68
    Activations Density 0.260%

    No Known Activations