© 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. 48469
    Prev
    Next
    INDEX
    Explanations

    R. followed by a letter or word

    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
    )
    -3.00
     моя
    -2.47
    ]
    -2.45
    }$.
    -2.44
     этот
    -2.30
    \
    -2.27
     это
    -2.27
     одной
    -2.23
     или
    -2.14
     treacherous
    -2.11
    POSITIVE LOGITS
    逦
    2.52
    綃
    2.42
    ”;
    2.19
     皇族
    1.98
    手紙
    1.93
     Años
    1.91
    妧
    1.89
     Nuestro
    1.88
     Ráp
    1.87
    缟
    1.87
    Activations Density 0.017%

    No Known Activations