© 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. 8677
    Prev
    Next
    INDEX
    Explanations

    the performance

    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
    0
    1.76
    1
    1.56
    2
    1.47
    5
    1.46
    6
    1.44
    4
    1.43
    3
    1.37
    7
    1.23
    8
    1.17
    9
    1.07
    POSITIVE LOGITS
     Націона
    0.93
    와
    0.92
     və
    0.91
    ючи
    0.91
     tə
    0.90
    וּ
    0.90
     আর
    0.89
    咊
    0.86
     теркәлүсез
    0.86
     آف
    0.85
    Activations Density 1.071%

    No Known Activations