© 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. 98178
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming constructs

    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
    𝕱
    -1.08
    itados
    -0.99
    vatten
    -0.98
    
    -0.98
     bocas
    -0.97
    総評
    -0.96
     lavorato
    -0.96
    )}$.
    -0.95
    ciclop
    -0.94
     garanzia
    -0.94
    POSITIVE LOGITS
     ebenso
    0.98
    is
    0.87
    mn
    0.86
    ’
    0.85
    R
    0.82
             
    0.79
    u
    0.78
     also
    0.78
    ,
    0.77
     essentiellement
    0.76
    Activations Density 0.027%

    No Known Activations