© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11181
    Prev
    Next
    INDEX
    Explanations

    color, colors, colour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    캥
    0.44
    イヤー
    0.43
     చెబు
    0.41
    บอก
    0.40
    赚
    0.39
    蓯
    0.39
     చెప్పారు
    0.38
    転車
    0.38
     बाथरूम
    0.38
    𒈥
    0.38
    POSITIVE LOGITS
    color
    0.63
    i
    0.54
     color
    0.53
    Color
    0.52
    colored
    0.50
    ForegroundColor
    0.48
    font
    0.48
    _
    0.47
     colour
    0.47
    en
    0.46
    Activations Density 0.000%

    No Known Activations