© 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. 1296
    Prev
    Next
    INDEX
    Explanations

    questions or requests for contact

    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
     künftig
    -1.36
     retrovisor
    -1.29
     teria
    -1.24
    定価
    -1.23
    入荷
    -1.21
    Whereas
    -1.21
    付属品
    -1.19
    麒麟
    -1.17
     tortura
    -1.16
    体温
    -1.16
    POSITIVE LOGITS
     these
    1.99
     appartamento
    1.63
     either
    1.59
     or
    1.55
     they
    1.50
     our
    1.47
     about
    1.47
     found
    1.41
     before
    1.41
    </tr>
    1.41
    Activations Density 0.025%

    No Known Activations