© 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. 53-GEMMASCOPE-2-RES-262K
    7. 50559
    Prev
    Next
    INDEX
    Explanations

    making something solid

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Grading
    0.42
    сього
    0.42
     seminal
    0.40
     दलों
    0.40
    시설
    0.38
     অফিসের
    0.37
    袭击
    0.37
     Guests
    0.37
     속
    0.37
     Radical
    0.36
    POSITIVE LOGITS
    ifying
    1.31
    ifies
    1.02
    ified
    1.02
    ification
    0.91
    ifiers
    0.82
    ificación
    0.82
    ifier
    0.81
    ifications
    0.79
    ify
    0.79
    िफिकेशन
    0.76
    Activations Density 0.010%

    No Known Activations