© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4720
    Prev
    Next
    INDEX
    Explanations

    leaving or left

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    5
    1.38
    9
    1.30
    3
    1.23
    1.19
    2
    1.10
    4
    1.10
    া
    1.05
    j
    1.05
     אם
    1.04
     идеи
    1.04
    POSITIVE LOGITS
    م
    1.44
    м
    1.10
    F
    1.05
    S
    1.04
    AT
    1.02
    AKT
    1.02
    X
    1.01
    ல்
    1.00
    ्स
    0.99
    िओ
    0.99
    Activations Density 0.089%

    No Known Activations