© 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-16K
    7. 12681
    Prev
    Next
    INDEX
    Explanations

    previous posts or events

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

    previous or past 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_16k_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
    ری
    0.71
    al
    0.63
     it
    0.61
     alku
    0.60
    ü
    0.60
    【
    0.59
     It
    0.59
     an
    0.57
    ش
    0.57
    ي
    0.57
    POSITIVE LOGITS
    previous
    1.02
    Previous
    0.96
     previous
    0.93
     الماض
    0.87
     Previous
    0.86
    past
    0.84
     предыду
    0.84
     గత
    0.80
     précédentes
    0.79
     प्रीवियस
    0.78
    Activations Density 0.211%

    No Known Activations