© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14344
    Prev
    Next
    INDEX
    Explanations

    code declarations and metadata

    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
     it
    -1.44
    },
    -1.28
     "+
    -1.24
     {\
    -1.13
     The
    -1.13
    -\\
    -1.13
     his
    -1.11
     their
    -1.10
     likely
    -1.10
     this
    -1.09
    POSITIVE LOGITS
    بسم
    1.39
    Nasc
    1.32
    Aggi
    1.29
     mít
    1.27
    Pengertian
    1.24
    憶
    1.24
    Eigenschaften
    1.23
    Forked
    1.22
    höhung
    1.22
     wichtigsten
    1.22
    Activations Density 0.000%

    No Known Activations