© 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. 34-GEMMASCOPE-RES-131K
    7. 55608
    Prev
    Next
    INDEX
    Explanations

    web automation tools

    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_34/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
     Palestina
    -0.93
    Дата
    -0.79
     mida
    -0.77
     Laden
    -0.76
    Charged
    -0.75
     школу
    -0.74
    babkan
    -0.73
     関連
    -0.73
    órm
    -0.72
     régional
    -0.72
    POSITIVE LOGITS
     agujero
    0.80
    proba
    0.77
     BeautifulSoup
    0.77
    AndWait
    0.77
    kuri
    0.76
    FFT
    0.72
     fría
    0.72
    selenium
    0.71
    rore
    0.71
    quakes
    0.71
    Activations Density 0.011%

    No Known Activations