© 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. 12214
    Prev
    Next
    INDEX
    Explanations

    news headlines and introductions

    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
     Dezember
    -0.73
    udayaan
    -0.72
     Milch
    -0.70
    						
    -0.70
     Raman
    -0.68
     deserved
    -0.65
     दु
    -0.65
    -```
    -0.64
    __*/
    -0.64
    ../../
    -0.64
    POSITIVE LOGITS
    ਦੀ
    0.77
    וצ
    0.77
     عالم
    0.76
     Prescription
    0.73
    rici
    0.73
    ughter
    0.71
     vienas
    0.71
    
    0.71
    σα
    0.71
    십시오
    0.70
    Activations Density 0.010%

    No Known Activations