© 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. 87009
    Prev
    Next
    INDEX
    Explanations

    programming and code contexts

    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
    Veranstal
    -1.27
    Aufbau
    -1.23
    Anmeldung
    -1.21
    Standort
    -1.18
    Only
    -1.15
    Größe
    -1.13
    Nachteile
    -1.13
     only
    -1.13
     başka
    -1.13
    Leistung
    -1.08
    POSITIVE LOGITS
    </h2>
    1.31
    tetlen
    1.30
     již
    1.30
    )`
    1.27
    TestingModule
    1.25
    )):
    1.23
    xdb
    1.23
    alış
    1.22
    zeichnis
    1.21
    quarto
    1.21
    Activations Density 0.007%

    No Known Activations