© 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. 80367
    Prev
    Next
    INDEX
    Explanations

    discover questions focusing minutes

    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
    ahar
    0.51
    வர்களின்
    0.49
    வர்களை
    0.47
    stakes
    0.47
     marts
    0.45
    emar
    0.44
     improvements
    0.43
     motivating
    0.43
     ä
    0.42
    hv
    0.42
    POSITIVE LOGITS
    Longueur
    0.46
     Branche
    0.44
    ンテ
    0.44
    ênd
    0.43
     रिलेशनशिप
    0.42
     bisog
    0.42
     লং
    0.42
    ڌ
    0.42
    Detail
    0.42
    Bag
    0.42
    Activations Density 0.001%

    No Known Activations