© 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. 111005
    Prev
    Next
    INDEX
    Explanations

    ph + common suffixes

    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
    in
    -3.59
    e
    -3.08
    er
    -3.05
    es
    -2.92
    re
    -2.38
    ка
    -2.38
     complet
    -2.36
    ized
    -2.28
    ization
    -2.27
    毟
    -2.27
    POSITIVE LOGITS
    횃
    3.05
    雳
    2.56
    styleable
    2.56
    瘩
    2.56
    翼翼
    2.50
     irritate
    2.44
     και
    2.42
    ឵
    2.39
    ്ട
    2.33
    筏
    2.31
    Activations Density 0.012%

    No Known Activations