© 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. 40758
    Prev
    Next
    INDEX
    Explanations

    however, therefore, contrast, consequence

    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
    л
    0.81
    يل
    0.79
     apparence
    0.79
    (
    0.74
     velocities
    0.73
    ב
    0.71
     gangsters
    0.69
     degrees
    0.66
     zuf
    0.66
     colds
    0.65
    POSITIVE LOGITS
    however
    0.89
    to
    0.80
     pertanto
    0.73
    ও
    0.70
     tuttavia
    0.68
    然而
    0.67
    ak
    0.67
    きた
    0.66
    在
    0.66
    therefore
    0.66
    Activations Density 0.020%

    No Known Activations