© 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-262K
    7. 215215
    Prev
    Next
    INDEX
    Explanations

    . option

    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_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
    卷积
    0.50
     بابەت
    0.50
     coseno
    0.43
     અલગ
    0.43
    expandindo
    0.43
    関数
    0.43
    䙷
    0.41
     convolutional
    0.41
    ិនបើ
    0.40
     BasicContainer
    0.40
    POSITIVE LOGITS
    />
    0.38
    ?>
    0.36
     Henderson
    0.35
     accented
    0.35
    ive
    0.35
    rzeb
    0.35
     />
    0.35
     supported
    0.34
    ↵↵↵
    0.34
     apparently
    0.34
    Activations Density 0.009%

    No Known Activations