© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132223
    Prev
    Next
    INDEX
    Explanations

    locations, dates, prices

    np_acts-logits-general · gemini-2.5-flash-lite

    columns and templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     هست
    0.49
     pruned
    0.48
    élève
    0.47
     hadron
    0.47
    sla
    0.46
     Kad
    0.45
     பிரச்சின
    0.45
     শ
    0.45
    nl
    0.45
     vl
    0.45
    POSITIVE LOGITS
    ज़
    0.51
    mvnrepository
    0.49
    返品
    0.48
    дова
    0.47
    のマ
    0.47
    कैसे
    0.46
    Полу
    0.46
    जीर
    0.46
    自治区
    0.46
    वाय
    0.45
    Activations Density 0.001%

    No Known Activations