© 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. 12242
    Prev
    Next
    INDEX
    Explanations

    projects and events

    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
     and
    -2.14
    cloudf
    -1.64
    anyakan
    -1.41
    }
    -1.38
    也许
    -1.38
    tokyo
    -1.38
    忸
    -1.36
    atürk
    -1.34
    künfte
    -1.34
     różnych
    -1.33
    POSITIVE LOGITS
     there
    1.63
    Recomendaciones
    1.55
    yelitis
    1.49
    R
    1.40
     asist
    1.37
     From
    1.36
    Conclusión
    1.34
    IFICATION
    1.34
     guter
    1.33
    佉
    1.30
    Activations Density 0.268%

    No Known Activations