© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8638
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
     your
    -1.99
     there
    -1.80
     you
    -1.70
    彼は
    -1.46
    NEYS
    -1.46
    even
    -1.38
    恚
    -1.36
    になるので
    -1.36
     this
    -1.34
     nying
    -1.34
    POSITIVE LOGITS
    ٥
    1.33
    Islamic
    1.28
    ٨
    1.27
    だが
    1.26
     film
    1.26
    ٦
    1.23
    )}\
    1.19
     movie
    1.18
    </h3>
    1.17
     kanske
    1.17
    Activations Density 0.127%

    No Known Activations