© 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. 9514
    Prev
    Next
    INDEX
    Explanations

    bullet points or list introductions

    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
     overwhelming
    0.74
    
    0.73
     inciting
    0.69
     причем
    0.68
     overpowering
    0.68
     вывод
    0.67
    עת
    0.67
     while
    0.65
     some
    0.65
     critic
    0.63
    POSITIVE LOGITS
    फ
    0.75
    Исход
    0.73
    ្នក
    0.72
     katva
    0.68
    شان
    0.67
    ld
    0.67
     ใด
    0.66
     consegn
    0.66
    TE
    0.66
    ší
    0.65
    Activations Density 1.981%

    No Known Activations