© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59321
    Prev
    Next
    INDEX
    Explanations

    will find

    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_34/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
     itself
    -1.30
    INCREF
    -0.98
    كل
    -0.94
    engeti
    -0.93
    pso
    -0.91
    鬟
    -0.89
    &__
    -0.88
    +#+#
    -0.87
     atriz
    -0.85
    henswürdigkeiten
    -0.85
    POSITIVE LOGITS
     find
    2.08
     notice
    1.73
     finds
    1.50
     see
    1.48
    พบ
    1.41
    Find
    1.38
     want
    1.37
     thấy
    1.34
     need
    1.32
    notice
    1.27
    Activations Density 0.028%

    No Known Activations