© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39573
    Prev
    Next
    INDEX
    Explanations

    plural forms and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vzdu
    -0.84
     telefonisch
    -0.82
     väč
    -0.80
     záz
    -0.80
     pasirink
    -0.79
    жке
    -0.77
    philo
    -0.77
     foll
    -0.76
    ꯩ
    -0.74
    bliž
    -0.73
    POSITIVE LOGITS
    jsko
    0.85
     behave
    0.84
    né
    0.83
    tu
    0.82
    oton
    0.81
    yship
    0.81
    無し
    0.80
    BorderSize
    0.79
    élev
    0.79
     derivatives
    0.78
    Activations Density 0.113%

    No Known Activations