© 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. 28327
    Prev
    Next
    INDEX
    Explanations

    end markers

    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
     найбіль
    -1.18
    aussi
    -1.02
    axl
    -1.02
     кӀ
    -0.99
    ajemy
    -0.96
     stále
    -0.96
     vitória
    -0.96
    collana
    -0.96
    četně
    -0.96
     durumu
    -0.96
    POSITIVE LOGITS
    }$.
    1.25
     without
    1.02
    paedia
    0.98
     yen
    0.92
     and
    0.92
     titu
    0.88
    </tr>
    0.87
    篆
    0.87
     before
    0.86
    зонта
    0.86
    Activations Density 0.008%

    No Known Activations