© 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. 10-GEMMASCOPE-RES-131K
    4. 102274
    Prev
    Next
    INDEX
    Explanations

    printers, Wong, jdbc, Lich

    np_acts-logits-general · gemini-2.5-flash-lite

    the token "prin" when it appears as part of words related to printing or printers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     którego
    -2.98
     któ
    -2.97
     którą
    -2.55
     ponieważ
    -2.53
     types
    -2.48
     dostępne
    -2.47
    ではある
    -2.44
    版本的
    -2.38
     gdyż
    -2.34
    ⬯
    -2.34
    POSITIVE LOGITS
    Getting
    2.42
    齮
    2.42
     kurzem
    2.39
    
    2.39
    ной
    2.36
     licorne
    2.33
    桖
    2.33
     célè
    2.33
     WHAT
    2.30
    A
    2.27
    Activations Density 0.006%

    No Known Activations