© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77679
    Prev
    Next
    INDEX
    Explanations

    keys followed by separators

    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_262k_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
    қа
    0.30
     sucrose
    0.28
    वाना
    0.28
    鰍
    0.28
    시아
    0.27
     iodine
    0.27
     Україні
    0.27
    ваясь
    0.27
     varnish
    0.26
    ໄ
    0.26
    POSITIVE LOGITS
     Nobody
    0.30
     பின்ப
    0.30
    并没有
    0.30
     volupt
    0.29
     никто
    0.29
     seconde
    0.29
     unimagin
    0.29
     conclus
    0.28
     enorm
    0.28
     inscr
    0.28
    Activations Density 0.008%

    No Known Activations