© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33499
    Prev
    Next
    INDEX
    Explanations

    university application

    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_all/layer_41_width_262k_l0_big
    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
     specificity
    0.39
    specificity
    0.37
    䀎
    0.37
     polici
    0.36
    Ainsi
    0.36
     expediente
    0.34
    咡
    0.34
    Ử
    0.33
    /}{
    0.33
    ಾತ
    0.33
    POSITIVE LOGITS
     Perhaps
    0.44
     Possibly
    0.44
     Suitable
    0.39
     Vielleicht
    0.39
     vielleicht
    0.38
     Worth
    0.38
     Maybe
    0.38
     misschien
    0.38
     подходит
    0.38
     maybe
    0.37
    Activations Density 0.000%

    No Known Activations