© 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-65K
    7. 46543
    Prev
    Next
    INDEX
    Explanations

    exquisite taste

    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
     pus
    0.50
     الجم
    0.47
     be
    0.45
     خواه
    0.43
     वाढत
    0.43
     pulleys
    0.41
    vk
    0.41
    鏟
    0.40
     gt
    0.40
     blotting
    0.40
    POSITIVE LOGITS
    ലൈ
    0.49
     reverted
    0.48
     humili
    0.48
    ະລ
    0.44
     nouvelles
    0.44
    {-#
    0.42
    劣化
    0.42
     connot
    0.42
     sadistic
    0.42
    reliant
    0.42
    Activations Density 0.010%

    No Known Activations