© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68568
    Prev
    Next
    INDEX
    Explanations

    start of phrases

    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
    Negative Logits
    
    -2.20
     offrir
    -1.81
    鎘
    -1.77
    Ciclo
    -1.76
    Tiempo
    -1.69
    ௅
    -1.66
    迨
    -1.63
    Ainsi
    -1.63
    獴
    -1.63
    Retour
    -1.59
    POSITIVE LOGITS
    >
    1.98
     time
    1.88
    }
    1.76
     last
    1.73
     way
    1.69
    。　
    1.68
    '}}>
    1.66
    From
    1.65
    ://
    1.63
     when
    1.61
    Activations Density 0.825%

    No Known Activations