© 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. 101916
    Prev
    Next
    INDEX
    Explanations

    word endings and segments

    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
     while
    -1.42
    Parque
    -1.31
     ensures
    -1.30
     hígado
    -1.27
     некоторые
    -1.26
     aslında
    -1.24
     blatantly
    -1.23
     during
    -1.22
    parque
    -1.22
     ostensibly
    -1.21
    POSITIVE LOGITS
     of
    1.76
    桖
    1.48
    ance
    1.43
    quels
    1.41
     qualquer
    1.41
     конкре
    1.38
    ation
    1.37
    鲥
    1.37
    ification
    1.33
    回戦
    1.33
    Activations Density 0.016%

    No Known Activations