© 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. 9301
    Prev
    Next
    INDEX
    Explanations

    Tim followed by a name

    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
    я
    3.23
    ة
    3.20
    a
    3.07
    es
    2.96
    ed
    2.61
    া
    2.57
    chod
    2.54
     destacado
    2.52
     самое
    2.49
    ा
    2.47
    POSITIVE LOGITS
    y
    3.86
    ्स
    3.57
    ્સ
    3.09
    s
    2.85
    ্স
    2.66
    
    2.57
    ്
    2.53
    self
    2.52
    م
    2.50
    də
    2.48
    Activations Density 0.062%

    No Known Activations