© 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. 22-GEMMASCOPE-RES-131K
    7. 431
    Prev
    Next
    INDEX
    Explanations

    log messages with numbers

    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_22/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
     suoi
    -1.02
    Away
    -0.95
    ni
    -0.91
    ちな
    -0.90
    bereiche
    -0.90
     ennen
    -0.88
    是一
    -0.86
    });
    -0.86
     Bereiche
    -0.85
    }
    -0.85
    POSITIVE LOGITS
     with
    1.27
    Waktu
    1.21
    Pemer
    1.07
    astien
    1.07
     nyeri
    1.06
    Informasi
    1.05
    Tous
    1.04
    过来了
    1.04
    كامل
    1.03
    廊下
    1.03
    Activations Density 0.002%

    No Known Activations