© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8898
    Prev
    Next
    INDEX
    Explanations

    further confirmation reinforce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    াচিত
    0.91
    ቄ
    0.85
     toch
    0.81
    omis
    0.81
     solução
    0.80
     address
    0.77
     sacrific
    0.77
     предлага
    0.77
     solución
    0.76
    혁
    0.76
    POSITIVE LOGITS
    延续
    1.47
     Repeating
    1.39
     extension
    1.37
     Extension
    1.35
     Extensions
    1.33
     दोहरा
    1.33
     repeating
    1.31
     extensions
    1.31
    延伸
    1.29
    Repeating
    1.29
    Activations Density 0.269%

    No Known Activations