© 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. 40162
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and code elements

    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
    وازم
    -0.91
    feito
    -0.91
     fontWeight
    -0.90
    对方的
    -0.89
     mód
    -0.88
     mág
    -0.87
     rám
    -0.86
    Neden
    -0.85
    یکر
    -0.84
     utford
    -0.84
    POSITIVE LOGITS
     tempera
    0.93
     Pristupljeno
    0.89
    zl
    0.89
    :
    
    0.88
     gemessen
    0.84
    ARD
    0.84
    му
    0.81
     trifft
    0.80
    V
    0.80
    将
    0.80
    Activations Density 0.172%

    No Known Activations