© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68832
    Prev
    Next
    INDEX
    Explanations

    weight in pounds

    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
     "
    -2.69
    0
    -2.55
    T
    -2.36
     glaring
    -2.22
     fisuras
    -2.17
     decked
    -2.09
     penchant
    -2.09
    The
    -2.09
     perpetrators
    -2.08
     prolonged
    -2.06
    POSITIVE LOGITS
    礡
    2.81
     菇
    2.63
    桫
    2.50
    麃
    2.44
    <bos>
    2.44
    
    2.31
    鯪
    2.31
    鱨
    2.30
    ſtra
    2.28
     NUEVO
    2.22
    Activations Density 0.004%

    No Known Activations