© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3222
    Prev
    Next
    INDEX
    Explanations

    just finished or completed

    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_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
     অন্যান্য
    0.87
     রাখে
    0.85
    illary
    0.79
     사람은
    0.79
     nantinya
    0.78
    Not
    0.78
     enthalten
    0.78
    琐
    0.78
     ومن
    0.76
     учитывать
    0.76
    POSITIVE LOGITS
     recently
    1.74
    recently
    1.63
     newly
    1.50
     Recently
    1.49
     recentemente
    1.43
    刚刚
    1.41
    Recently
    1.39
     recientemente
    1.30
     selesai
    1.29
     freshly
    1.28
    Activations Density 0.019%

    No Known Activations