© 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. 46080
    Prev
    Next
    INDEX
    Explanations

    percentages, proportions, and ratios

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

    proportion percentage ratio

    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
     kayıt
    0.45
    plikasi
    0.42
    귀
    0.42
    dyn
    0.42
     açık
    0.42
    +="
    0.41
    హు
    0.41
    邑
    0.41
    കൂ
    0.40
    กระ
    0.39
    POSITIVE LOGITS
     percentage
    1.63
     proportion
    1.63
     percentages
    1.61
     비율
    1.53
     percentuale
    1.52
    割合
    1.48
     Percentage
    1.46
     ratio
    1.45
    比例
    1.43
     Proportion
    1.43
    Activations Density 0.104%

    No Known Activations