© 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. 10-GEMMASCOPE-RES-131K
    7. 10056
    Prev
    Next
    INDEX
    Explanations

    from X to Y

    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_10/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
    /
    -1.22
     هستید
    -1.22
    了好
    -1.20
     zwar
    -1.20
     ausser
    -1.19
    R
    -1.19
     لكن
    -1.17
     neither
    -1.17
     большо
    -1.16
    #
    -1.16
    POSITIVE LOGITS
    衎
    1.42
     battaglia
    1.34
    而不是
    1.34
     instead
    1.32
    días
    1.27
     вместо
    1.26
     virtù
    1.25
    Теперь
    1.25
     progettazione
    1.23
     bentuk
    1.20
    Activations Density 0.066%

    No Known Activations