© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68082
    Prev
    Next
    INDEX
    Explanations

    String type or string variable

    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
    枡
    -1.52
     elle
    -1.39
     många
    -1.30
     ),
    -1.30
    刁
    -1.29
     également
    -1.27
    emann
    -1.27
     \\
    -1.27
     realmente
    -1.26
    NewUrlParser
    -1.26
    POSITIVE LOGITS
     seguenti
    1.47
     this
    1.41
     while
    1.41
     Hvor
    1.35
     when
    1.27
     only
    1.26
    "/",
    1.25
     discussione
    1.24
     PHILADELPHIA
    1.23
     geheel
    1.21
    Activations Density 0.027%

    No Known Activations