© 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-16K
    7. 6668
    Prev
    Next
    INDEX
    Explanations

    percentages and calculations

    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_16k_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
    ジット
    0.43
     oeste
    0.42
    вета
    0.41
     estuvieron
    0.40
     প্রার্থী
    0.39
    ⬯
    0.39
    ھے
    0.39
     Solicitor
    0.39
    ەس
    0.38
     yıldır
    0.38
    POSITIVE LOGITS
    },
    0.54
     Nylon
    0.42
     नाभ
    0.42
    licher
    0.41
    NV
    0.41
     Natl
    0.41
     traceback
    0.41
     NBS
    0.41
     NV
    0.41
    nd
    0.40
    Activations Density 0.086%

    No Known Activations