© 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. 41405
    Prev
    Next
    INDEX
    Explanations

    statement endings in code

    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
    秆
    -1.18
    だそうです
    -1.18
    this
    -1.15
    <h2>
    -1.14
     thorough
    -1.13
    Either
    -1.13
    jścia
    -1.12
    venske
    -1.10
     into
    -1.09
     From
    -1.09
    POSITIVE LOGITS
     their
    1.50
    以及
    1.41
     or
    1.39
    </h4>
    1.38
     тобой
    1.30
    นะคะ
    1.30
     gdzie
    1.30
     who
    1.23
     alrededores
    1.20
     маленький
    1.19
    Activations Density 0.008%

    No Known Activations