© 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. 34-GEMMASCOPE-RES-131K
    7. 65772
    Prev
    Next
    INDEX
    Explanations

    magnitude and degree

    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_34/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
     of
    -1.48
     approach
    -1.06
     whose
    -1.01
     Verhältnisse
    -1.00
     that
    -0.98
    くらいの
    -0.96
     losing
    -0.96
    ajuste
    -0.93
     emerged
    -0.92
     gesehen
    -0.92
    POSITIVE LOGITS
     demais
    1.15
    itize
    1.01
     enough
    1.00
    ☑️
    0.96
    ToDate
    0.94
    rC
    0.94
     största
    0.94
    
    0.92
     celles
    0.91
    Ведь
    0.91
    Activations Density 0.120%

    No Known Activations