© 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. 10-GEMMASCOPE-RES-131K
    7. 129871
    Prev
    Next
    INDEX
    Explanations

    moving followed by preposition or adverb

    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
    过于
    -2.56
     kredi
    -2.50
    人の
    -2.50
     elektri
    -2.47
     остальные
    -2.34
     kunde
    -2.30
    一直在
    -2.22
     etik
    -2.22
     diki
    -2.17
    一根
    -2.16
    POSITIVE LOGITS
    蠃
    3.09
    नलोड
    2.92
     That
    2.70
    屃
    2.67
    晅
    2.67
    an
    2.59
    玙
    2.56
     wohin
    2.56
    ."
    2.53
     moving
    2.52
    Activations Density 0.008%

    No Known Activations