© 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. 7243
    Prev
    Next
    INDEX
    Explanations

    color names

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

    colors

    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
    ल
    0.57
    л
    0.56
     accad
    0.54
     importants
    0.51
    एक
    0.48
     acte
    0.47
     dwRes
    0.47
     اداروں
    0.46
     omfatt
    0.46
    ു
    0.46
    POSITIVE LOGITS
    色的
    1.02
    色の
    0.90
     colored
    0.84
    colored
    0.78
     রঙের
    0.77
     color
    0.76
     coloured
    0.72
     tinge
    0.70
     green
    0.70
     discoloration
    0.68
    Activations Density 0.205%

    No Known Activations