© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48477
    Prev
    Next
    INDEX
    Explanations

    end of phrases

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    fangs
    0.51
    顾客
    0.48
    <unused73>
    0.46
    lijk
    0.45
    warranty
    0.45
    StillWater
    0.45
    Warranty
    0.45
    mLogin
    0.45
    digits
    0.44
    Maine
    0.43
    POSITIVE LOGITS
     z
    0.45
     n
    0.43
     Selector
    0.43
    :
    0.42
     distorted
    0.42
     cardboard
    0.42
     maxima
    0.40
     zm
    0.40
     cropping
    0.40
     whispering
    0.39
    Activations Density 0.004%

    No Known Activations