© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2127
    Prev
    Next
    INDEX
    Explanations

    measurements with units

    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_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
    पटॉप
    0.56
    ους
    0.51
     وتح
    0.50
    एगी
    0.50
    啇
    0.49
    嘊
    0.49
    <unused520>
    0.49
     डेफिनेशन
    0.48
     لگائیں
    0.48
    🔈
    0.48
    POSITIVE LOGITS
    dental
    0.52
    Mini
    0.49
    ERCE
    0.49
    ﻙ
    0.48
     maternity
    0.47
    izante
    0.47
     renters
    0.46
    tant
    0.46
    xas
    0.46
     sleepy
    0.46
    Activations Density 0.000%

    No Known Activations