© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213069
    Prev
    Next
    INDEX
    Explanations

    "nine" or numbers squared

    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_40_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
     squared
    0.46
     squaring
    0.44
     제곱
    0.41
    IBR
    0.39
    squared
    0.39
    龋
    0.38
    square
    0.38
    дел
    0.38
    quadratic
    0.38
    🏽
    0.38
    POSITIVE LOGITS
     nine
    0.84
     neun
    0.81
     Nine
    0.77
    Nine
    0.77
    nine
    0.76
     nueve
    0.67
    九
    0.67
     девя
    0.66
     九
    0.61
     नाइन
    0.59
    Activations Density 0.029%

    No Known Activations