© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184139
    Prev
    Next
    INDEX
    Explanations

    future direction

    np_acts-logits-general · gemini-2.5-flash-lite

    apple products and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     因為
    0.50
     インド
    0.48
    ),]$
    0.48
    盜
    0.48
     ซ
    0.47
     重
    0.47
     中国
    0.46
     除
    0.46
    UT
    0.46
     ఇండి
    0.45
    POSITIVE LOGITS
     improvements
    0.50
     dictates
    0.50
     betterment
    0.50
     manly
    0.50
     velocities
    0.49
     pillars
    0.49
     theatres
    0.48
     perfection
    0.47
     disrupt
    0.47
     eminently
    0.47
    Activations Density 0.000%

    No Known Activations