© 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. 31-GEMMASCOPE-2-RES-65K
    7. 14160
    Prev
    Next
    INDEX
    Explanations

    each

    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_65k_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
     prijs
    0.43
    elat
    0.42
    ův
    0.41
    nější
    0.41
    ině
    0.40
    जफ्
    0.39
    =","><
    0.39
     namelijk
    0.39
     τρο
    0.39
    려
    0.39
    POSITIVE LOGITS
     each
    0.70
     каждого
    0.68
     каждое
    0.63
     каждом
    0.59
     fiecare
    0.58
     każde
    0.58
     каждый
    0.57
     каждым
    0.57
     всеки
    0.56
     EACH
    0.55
    Activations Density 0.054%

    No Known Activations