© 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. 58638
    Prev
    Next
    INDEX
    Explanations

    calculating or computing

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

    calculates values

    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
    یک
    0.84
    ियों
    0.81
    ید
    0.79
    ﻦ
    0.75
    یا
    0.72
    یم
    0.72
    <unused40>
    0.68
    دی
    0.67
    なく
    0.66
     Бүгенге
    0.66
    POSITIVE LOGITS
     calculates
    0.94
    an
    0.93
     calculate
    0.91
     calcula
    0.86
     Calculate
    0.84
     computes
    0.84
     calculation
    0.84
    計算
    0.84
    calcul
    0.83
     calcular
    0.83
    Activations Density 0.010%

    No Known Activations