© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21602
    Prev
    Next
    INDEX
    Explanations

    tree or stump

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ງານ
    0.49
     weave
    0.45
     basket
    0.44
     weaves
    0.41
     conducir
    0.41
    ке
    0.41
     empleados
    0.41
    ❸
    0.40
     infused
    0.40
     thơ
    0.40
    POSITIVE LOGITS
    পালা
    0.50
     Stump
    0.48
    🌲
    0.48
    ਮ
    0.46
     Hug
    0.43
     stump
    0.42
     TreeNode
    0.42
    እ
    0.42
    ఎ
    0.41
     ITF
    0.41
    Activations Density 0.004%

    No Known Activations