© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48816
    Prev
    Next
    INDEX
    Explanations

    numbers and code types

    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_40_width_65k_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
     Strengthening
    0.45
     Strengthen
    0.43
    ⼈
    0.43
     IMPRO
    0.42
     Throw
    0.41
     CHO
    0.41
     साम्राज्य
    0.41
     beets
    0.40
     outweighed
    0.39
     outperforms
    0.39
    POSITIVE LOGITS
    eng
    0.45
    ua
    0.40
    ep
    0.40
    یدر
    0.39
     K
    0.38
    process
    0.38
    cleanup
    0.38
    static
    0.38
     processo
    0.38
     passent
    0.38
    Activations Density 0.004%

    No Known Activations