© 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. 10-GEMMASCOPE-RES-131K
    7. 10164
    Prev
    Next
    INDEX
    Explanations

    the advent of new developments

    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_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
    <bos>
    -1.77
    饜
    -1.76
     delicioso
    -1.66
    驁
    -1.59
    tennis
    -1.55
    sữa
    -1.53
    sistent
    -1.50
    ceptable
    -1.48
    
    -1.45
     décision
    -1.42
    POSITIVE LOGITS
    k
    1.73
     Always
    1.55
    t
    1.54
     дверей
    1.46
     afectar
    1.45
    li
    1.41
    a
    1.39
    书籍
    1.38
    各式
    1.38
     From
    1.37
    Activations Density 0.039%

    No Known Activations