© 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. 142141
    Prev
    Next
    INDEX
    Explanations

    opinions and conditions

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

    valuation and capabilities

    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
     '
    0.57
     diameter
    0.51
     Darius
    0.51
     min
    0.50
     darum
    0.49
     Louis
    0.48
     max
    0.47
     holo
    0.47
     maxim
    0.46
     umbrella
    0.45
    POSITIVE LOGITS
    κ
    0.63
    笘
    0.53
     обеспечивает
    0.52
    手指
    0.51
    的女
    0.50
    的他
    0.50
    కూ
    0.49
    耇
    0.49
    的国家
    0.49
    Partido
    0.48
    Activations Density 0.000%

    No Known Activations