© 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. 234
    Prev
    Next
    INDEX
    Explanations

    loading and abuse

    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
     النساء
    -1.52
    𝗨
    -1.52
    '
    -1.40
    鮋
    -1.39
    <td>
    -1.39
     alway
    -1.38
     Facultad
    -1.37
    euvres
    -1.36
    Ambos
    -1.36
    ionalmente
    -1.34
    POSITIVE LOGITS
    </em>
    1.55
    就
    1.44
     Մ
    1.42
    当
    1.37
    üche
    1.37
    </sup>
    1.34
     Ռ
    1.32
     durante
    1.29
    我们
    1.28
    出發
    1.27
    Activations Density 0.001%

    No Known Activations