© 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-262K
    7. 248933
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     theologians
    0.49
     diminish
    0.48
     purses
    0.44
     vínculos
    0.44
     chains
    0.42
     Catarina
    0.42
     swipes
    0.42
    =")
    0.41
     mathematicians
    0.41
     =",
    0.41
    POSITIVE LOGITS
    間の
    0.58
    Neue
    0.51
    wellness
    0.47
    を楽しむ
    0.46
    Xbox
    0.46
    CL
    0.46
    stech
    0.45
    fast
    0.45
    ѕ
    0.44
    حر
    0.44
    Activations Density 0.001%

    No Known Activations