© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8951
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action

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

    list items and titles

    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_40_width_16k_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
     बजा
    0.46
    
    0.45
    пры
    0.42
    ➋
    0.42
    ㄥ
    0.41
     মাঝে
    0.41
     leapt
    0.40
     เอง
    0.40
    💾
    0.39
    やす
    0.39
    POSITIVE LOGITS
    elh
    0.41
     جو
    0.40
     Nathalie
    0.40
     Jo
    0.38
    cherichia
    0.38
    туу
    0.37
     صد
    0.37
    etl
    0.37
    ROG
    0.37
    Ро
    0.36
    Activations Density 0.002%

    No Known Activations