© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9110
    Prev
    Next
    INDEX
    Explanations

    me to

    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_9_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
    le
    3.48
    д
    3.03
    ers
    2.90
    ेक्स
    2.89
    า
    2.87
    ي
    2.87
    Complaint
    2.81
    ী
    2.79
    స్
    2.71
    
    2.68
    POSITIVE LOGITS
     thereto
    3.35
     إليه
    2.94
     إليها
    2.86
     to
    2.69
    ات
    2.45
    coes
    2.41
     posi
    2.35
    nan
    2.31
     jsonify
    2.27
     fir
    2.27
    Activations Density 0.332%

    No Known Activations