© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2361
    Prev
    Next
    INDEX
    Explanations

    processes of creation and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    हुन्छ
    0.87
     спраши
    0.82
    izaciones
    0.81
     deje
    0.80
    znym
    0.79
    勉強
    0.79
     когда
    0.77
    㚐
    0.75
    ણો
    0.74
     মানুষ
    0.73
    POSITIVE LOGITS
     کردن
    0.99
    ירת
    0.85
     شدن
    0.85
    abling
    0.80
    และการ
    0.79
     unor
    0.77
    owanie
    0.76
    uing
    0.76
    ierung
    0.76
     ء
    0.74
    Activations Density 0.247%

    No Known Activations