© 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. 22-GEMMASCOPE-RES-131K
    4. 9376
    Prev
    Next
    INDEX
    Explanations

    currency symbols and punctuation

    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_22/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
    いただきます
    -1.02
     at
    -0.90
    aos
    -0.90
     brilliant
    -0.89
    ポスター
    -0.88
    when
    -0.88
    ciptakan
    -0.88
    つまり
    -0.87
     when
    -0.85
     burgeoning
    -0.85
    POSITIVE LOGITS
    €,
    1.23
    ?»
    1.15
    richtet
    1.11
     ')
    
    1.11
     "];
    1.10
    €.
    1.10
     €,
    1.09
    !»
    1.08
    ());
    
    1.06
    )));
    1.06
    Activations Density 0.037%

    No Known Activations